The use of autonomous unmanned aerial vehicle (UAV) swarms for area coverage requires efficient coverage path planning (CPP) strategies that ensure complete exploration while minimizing maneuvering effort, energy consumption, and collision risk. This paper proposes a distributed computational framework for swarm-based patrolling using CPP algorithms. The framework integrates Bézier-curve trajectory smoothing and safety-distance constraints to generate dynamically feasible and collision-free paths. A capability-aware space decomposition method partitions the target region into convex subareas, enabling parallel coverage while accounting for UAV configuration and platform capabilities. Swarm-adapted versions of Parallel, Square, LMAT, and SCAN strategies are developed to generate intra- and inter-subregion coverage paths. Experimental validation using a homogeneous swarm of four quadcopters demonstrates reduced computational complexity and turning maneuvers while producing smooth and continuous trajectories, enabling efficient large-area coverage with improved operational endurance.

We argue that traditional 2D hyperspectral imaging is not adapted to many modern challenges. With the rise of high spatial resolution, hyperspectral sensors mounted on different platforms (e.g. drones, terrestrial, satellites) and innovative applications (e.g. urban mapping, mining monitoring), projections, occlusions, perspective effects and data processing limit the use of 2D hyperspectral imaging. We propose that 3D hyperclouds, in which Lidar or photogrammetric point clouds are augmented with hyperspectral attributes, can address numerous of these challenges. We demonstrate the benefits of hyperclouds and dedicated machine learning architectures with several realistic examples.

Despite the extensive body of research conducted on the fusion of lidar and hyperspectral data for land cover classification in urban areas, the predominant approach has been the utilization of rasterized lidar data merged with hyperspectral data. This image-centric methodology tends to overlook the primary advantage inherent in lidar technology—namely, the production of 3D point cloud data. In our work, we present a framework demonstrating how we infer semantic information from 3D point cloud data, comprising both lidar and hyperspectral features—a concept we refer to as a 3D hyperspectral point cloud. We illustrate the generation of hyperspectral point clouds and evaluate the performance of various deep learning models for point learning. Our findings on the original test data of the 2018 IEEE GRSS Data Fusion Challenge, disclosed by IEEE Image Analysis and Data Fusion Technical Committee, indicate that recent deep learning models not only produce better shapes for predicted objects but also yield more precise semantic information. Finally, we plan to release the 3D hyperspectral point cloud data to the community, hoping to inspire future studies on data fusion in the point cloud domain.

Mining change detection requires dedicated datasets because it includes unique objects such as pits or quarries, tailings dams, overburden, processing plants, haul roads, access roads, buildings/sheds, mining and blasting equipment, and plants, among others. This paper introduces a benchmark, large dataset for mining change detection, termed the MineNet-CD, to facilitate large-scale change detection. The proposed dataset contains a total of 100 high-resolution bi-temporal mining images from all over the world with corresponding ground truth. Unlike existing datasets, the images of MineNet-CD exhibit significant background, topological variation, and well-defined ground truth that ignores insignificant change maps. The work analyzes the efficacy of state-of-the-art deep learning methods for change detection. The results demonstrate that more efficient and advanced networks are required to accurately predict the change maps. The dataset and code are available at https://github.com/EricYu97/MineNet-CD.

The increasing use of deep learning techniques has reduced interpretation time and, ideally, reduced interpreter bias by automatically deriving geological maps from digital outcrop models. However, accurate validation of these automated mapping approaches is a significant challenge due to the subjective nature of geological mapping and the difficulty in collecting quantitative validation data. Additionally, many state-of-the-art deep learning methods are limited to 2D image data, which is insufficient for 3D digital outcrops, such as hyperclouds. To address these challenges, we present Tinto, a multi-sensor benchmark digital outcrop dataset designed to facilitate the development and validation of deep learning approaches for geological mapping, especially for non-structured 3D data like point clouds. Tinto comprises two complementary sets: 1) a real digital outcrop model from Corta Atalaya (Spain), with spectral attributes and ground-truth data, and 2) a synthetic twin that uses latent features in the original datasets to reconstruct realistic spectral data (including sensor noise and processing artifacts) from the ground-truth. The point cloud is dense and contains 3,242,964 labeled points. We used these datasets to explore the abilities of different deep learning approaches for automated geological mapping. By making Tinto publicly available, we hope to foster the development and adaptation of new deep learning tools for 3D applications in Earth sciences. The dataset can be accessed through this link: https://doi.org/10.14278/rodare.2256.

Monitoring land changes triggered by mining activities is crucial for industrial control, environmental management, and regulatory compliance, yet it poses significant challenges due to the vast and often remote locations of mining sites. Remote sensing technologies have increasingly become indispensable to detect and analyze these changes over time. We thus introduce MineNetCD, a comprehensive benchmark designed for global mining change detection using remote sensing imagery. The benchmark comprises three key contributions. First, we establish a global mining change detection dataset featuring more than 70k paired patches of bitemporal high-resolution remote sensing images and pixel-level annotations from 100 mining sites worldwide. Second, we develop a novel baseline model based on a change-aware fast Fourier transform (ChangeFFT) module, which enhances various backbones by leveraging essential spectrum components within features in the frequency domain and capturing the channelwise correlation of bitemporal feature differences to learn change-aware representations. Third, we construct a unified change detection (UCD) framework that currently integrates 20 change detection methods. This framework is designed for streamlined and efficient processing, using the cloud platform hosted by HuggingFace. Extensive experiments have been conducted to demonstrate the superiority of the proposed baseline model compared with 19 state-of-the-art change detection approaches. Empirical studies on modularized backbones comprehensively confirm the efficacy of different representation learners on change detection. This benchmark represents significant advancements in the field of remote sensing and change detection, providing a robust resource for future research and applications in global mining monitoring. Dataset and Codes are available via the link.

Since many materials behave as heterogeneous intimate mixtures with which each photon interacts differently, the relationship between spectral reflectance and material composition is very complex. Quantitative validation of spectral unmixing algorithms requires high-quality ground truth fractional abundance data, which are very difficult to obtain.In this work, we generated a comprehensive hyperspectral dataset of intimate mineral powder mixtures by homogeneously mixing five different clay powders (Kaolin, Roof clay, Red clay, mixed clay, and Calcium hydroxide). In total 325 samples were prepared. Among the 325 samples, 60 mixtures were binary, 150 were ternary, 100 were quaternary, and 15 were quinary. For each mixture (and pure clay powder), reflectance spectra are acquired by 13 different sensors, with a broad wavelength range between the visible and the long-wavelength infrared regions (i.e., between 350 nm and 15385 nm) and with a large variation in sensor types, platforms, and acquisition conditions. We will make this dataset public, to be used by the community for the validation of nonlinear unmixing methodologies (https://github.com/VisionlabUA/Multisensor_datasets)

Hyperspectral datasets obtained from a specific sensor can experience changes in their characteristics due to environmental noise and variations in illumination. Consequently, a segmentation model trained on one dataset may struggle to accurately predict labels and detect objects on a different dataset due to discrepancies between the two domains. To overcome this challenge, domain adaptation techniques can be employed. In the paper, we study hyperspectral domain adaptation for adapting the target domain to align with the source domain in detecting the material type of mm-scale particles from shredded electrolyzers on a conveyor belt for recycling applications. This is necessary due to the non-uniform distribution of particles, variations in material types, and changes in the imaging environment. The results show improvements compared to a pre-trained model using a 2D convolutional neural network.

In this paper, we propose a deep learning-based hyperspectral inpainting (DeepHyIn). The proposed approach is unsupervised since it only utilizes the observed image for training the network. First, we propose a novel model for hyperspectral inpainting in which the degraded hyperspectral image is a linear mixture of endmembers and degraded abundances. The proposed model is subjected to abundance sum to one and nonnegativity constraints. We further assume that the endmembers are known. Then, we propose an optimization problem to estimate the unknown abundance using an image prior. Inspired by deep image prior, we shift the optimization problem to optimize the parameters of a deep network. The proposed method uses a deep convolutional encoder-decoder architecture as a backbone. Finally, we apply the DeepHyIn to the Samson dataset and evaluate the results. DeepHyIn demonstrates considerable quantitative and qualitative improvements compared with the state-of-the-art. DeepHyIn was implemented in Python (3.9) using PyTorch as the platform for the deep network and is available online: https://github.com/BehnoodRasti/DeepHyIn.

Hyperspectral imaging is an important technology in the field of geosciences and remote sensing.However, the highdimensional nature of hyperspectral images (HSIs) together with the limited availability of training/labeled samples challenge an efficient processing of HSIs.To alleviate these challenges, we propose a deep multi-resolution clustering network (DMC-Net) to analyze HSIs.DMC-Net, without requiring training/labeled samples for the training process, captures the non-linear intrinsic relation within data points in an HSI and analyzes the image at various resolutions by applying atrous convolutions.Furthermore, DMC-Net preserves the spectral information by directly incorporating extracted features from the original HSI into the reconstruction phase.In terms of clustering accuracy, experimental results on two real HSIs demonstrate the superior performance of DMC-Net compared to the state-of-the-art deep learning-based clustering approaches.

We propose a new fusion-based classification technique for optical multisource remote-sensing images called OptFus. OptFus is developed to merge and process optical imagery having different spatial and spectral resolutions. The spatial features are extracted using morphological filters from the RGB data containing high spatial resolution. A feature fusion technique is developed to combine all the sensor data in a subspace using a common set of representative features. Finally, the fused features are classified using a support vector machine to ensure a robust supervised spectral classification. The proposed method is designed to allocate varying weights to the data from various imaging sensors in the fusion process. OptFus is applied to two multisource optical datasets captured from geological drill-core samples. The classification accuracy demonstrates considerable improvements compared to the state-of-the-art. A MATLAB implementation of OptFus is available online:https://github.com/BehnoodRasti/OptFus.

Deep subspace clustering has achieved remarkable performances in the unsupervised classification of hyperspectral images. However, previous models based on pixel-level self-expressiveness of data suffer from the exponential growth of computational complexity and access memory requirements with increasing number of samples, thus leading to poor applicability to large hyperspectral images. This paper presents a Neighborhood Contrastive Subspace Clustering network (NCSC), a scalable and robust deep subspace clustering approach, for unsupervised classification of large hyperspectral images. Instead of using a conventional autoencoder, we devise a novel superpixel pooling autoencoder to learn the superpixel-level latent representation and subspace, allowing a contracted self-expressive layer. To encourage a robust subspace representation, we propose a novel neighborhood contrastive regularization to maximize the agreement between positive samples in subspace. We jointly train the resulting model in an end-to-end fashion by optimizing an adaptively weighted multi-task loss. Extensive experiments on three hyperspectral benchmarks demonstrate the effectiveness of the proposed approach and its substantial advancement of state-of-the-art approaches.

The widespread application of drones and associated miniaturization of imaging sensors has led to an explosion of remote sensing applications with very high spatial and spectral resolutions. The 3-D ultrahigh-resolution digital outcrop models created using drones and oblique imagery from ground-based sensors are now commonly used in the academic and industrial sectors, while the generation of spatially accurate models has been greatly facilitated by the development of computer vision tools, such as structure from motion, and the correction of spectral attributes to achieve material reflectance measurements remains challenging. Following the development of a topographical correction toolbox (mephysto), we now propose a series of new tools that can leverage the detailed geometry captured by digital outcrop models to correct for illumination effects caused by oblique viewing angles and the interaction of light with complex 3-D surfaces. This open-source code is integrated intohylite, a python toolbox for the full 3-D processing and fusion of digital outcrop models with hyperspectral imaging data. We validate the performance of our novel method using a case study at an open-pit mine in Tharsis, Spain, and demonstrate the importance of accurate illumination corrections for quantitative spectral analyses. Significantly, we show that commonly applied spectral analysis techniques can yield erroneous results for data corrected using current state-of-the-art approaches. Our proposed method ameliorates many of the issues with these established approaches.

Drones are getting more and more used to replace piloted platforms to reduce the costs and increase safety of activities such as monitoring, delivery or warfare. So far though, drones have barely been used as more than single-sensor platforms. In order to be used in mineral exploration we need to ensure that the data acquired by drones are versatile, accurate and adapted to the tasks but also that the platforms are robust and low-maintenance to ensure an operational use in remote locations. During the last years we developed and tested a series of workflows to rapidly provide relevant information to exploration teams. It starts with multi-source data acquisition, data integration and preprocessing. We then use machine learning to process the data and generate relevant geological information.

Geological mapping in difficult-to-access terrain such as open pit mines often relies on remotely sensed data. Hyperspectral data yield valuable geological information, especially when spectral ranges of multiple sensors are used in conjunction. In this contribution we project a number of hyperspectral datasets of an open pit mine covering the visible to near-infrared (VNIR), short-wave infrared (SWIR), and long-wave infrared (LWIR) range from airborne, drone-borne and ground-based acquisitions into a photogrammetric point cloud. The resulting hyperspectral digital outcrop is then used as a basis for data integration in a 3D environment. To discriminate geologic materials in the pit we apply a Gaussian deconvolution to identify the position of diagnostic absorption features in the SWIR and LWIR, and then apply a support vector machine-based classification. Our results agree with known lithologic units and alteration patterns and can be used to guide exploration targeting and mine planning.

We present an analysis of the influence of noise on the unmixing of hyperspectral data. We propose four scenarios to 1) investigate the effect of noise reduction as a preprocessing step on the performance of hyperspectral unmixing and 2) study the relation between noise and different endmembers selection strategies. Experiments are conducted on a simu-1ated and a real datasets with a wide range of signal to noise ratios (from 10 to 50 dB).

Remote sensing data is contaminated with different types of noise that can severely affect the analysis of this data. Generally, in modern treatment chains of satellite and aerial data, denoising techniques are applied to atmospherically corrected images prior to further analysis (e.g., classification). However, since the noise contaminates the measured radiance at the sensor, it can influence the atmospheric correction in itself and consequently the remaining of the processing chain. In this paper, we compare the performance of a denoising technique, when applied before or after atmospheric correction. Our observations challenge the current de facto paradigm of denoising in a processing chain of spaceborne and airborne remotely sensed images.

The inclusion of spatial information into spectral classifiers for fine-resolution hyperspectral imagery has led to significant improvements in terms of classification performance. The task of spectral-spatial hyperspectral image (HSI) classification has remained challenging because of high intraclass spectrum variability and low interclass spectral variability. This fact has made the extraction of spatial information highly active. In this work, a novel HSI classification framework using the fusion of dual spatial information is proposed, in which the dual spatial information is built by both exploiting pre-processing feature extraction and post-processing spatial optimization. In the feature extraction stage, an adaptive texture smoothing method is proposed to construct the structural profile (SP), which makes it possible to precisely extract discriminative features from HSIs. The SP extraction method is used here for the first time in the remote sensing community. Then, the extracted SP is fed into a spectral classifier. In the spatial optimization stage, a pixel-level classifier is used to obtain the class probability followed by an extended random walker-based spatial optimization technique. Finally, a decision fusion rule is utilized to fuse the class probabilities obtained by the two different stages. Experiments performed on three data sets from different scenes illustrate that the proposed method can outperform other state-of-the-art classification techniques. In addition, the proposed feature extraction method, i.e., SP, can effectively improve the discrimination between different land covers.

Hyperspectral imaging plays an important role for mineral mapping in a nondestructive and noninvasive way. In this paper, a novel resolution enhancement method is proposed based on the principle of intrinsic image decomposition for mineral mapping. This method is based on an assumption that hyperspectral image (HSI) can be decomposed into a reflectance component and an illumination component. Based on this idea, the RGB image is first transformed into Intensity-Hue-Saturation (IHS) space, and the intensity channel is considered as the illumination component of the HSI with an ideal high spatial resolution. Then, the reflectance component of the ideal HSI is estimated with the downsampled HSI image and the downsampled intensity channel. Finally, the HSI with high resolution can be reconstructed by utilizing the estimated illumination and the reflectance components. Experimental results validate the effectiveness of the proposed method qualitatively and quantitatively by outperforming several state-of-the-art approaches.

This paper brings together advances in remote sensing and deep learning for mineral mapping in a sustainable way. In more detail, we propose a multisensor feature fusion approach to integrate heterogeneous RGB, multispectral, and hyperspectral images for sustainable mining. The proposed approach is composed of two main steps; Feature extraction and classification. In the feature extraction step, we develop a three-stream convolutional neural network to extract high-level information from the input multisensor data. In the classification step, we develop a multisensor composite kernel approach to perform fusion and mapping simultaneously. The proposed approach produces very high quality classification maps with exceptional results in terms of classification accuracies.

Accurately mapping lithology and geological structures remains a challenge in rough terrain or in active mining areas. We propose that the integration of terrestrial and drone-borne multi-sensor remote sensing techniques can significantly boost the reliability, safety, and efficiency of geological activities in exploration and for the monitoring of mining activities. We have now developed a complete procedural chain to jointly and accurately process Structure-from-Motion Multi-View Stereo point clouds and hyperspectral data cubes in the visible to near-infrared (VNIR) and short-wave infrared (SWIR), as well as long-wave infrared (LWIR) ranges acquired by terrestrial sensors. Hyperspectral data are processed using spectroscopic and machine learning algorithms to generate meaningful 2.5D (i.e., surface) maps that are available to geologists on the ground shortly after data acquisition. We classify the geological information content using innovative machine learning techniques. We validate the remote sensing data with in-situ mineralogical and structural measurements. Repeated acquisitions allow then to integrate a time component.

This paper presents a technique for the fusion of multispectral LiDAR and hyperspectral data. The proposed method is based on the fusion of the features of multispectral LiDAR and hyperspectral data projected in two different subspaces. First, the spatial features are extracted from both data using morphological filters. Then, the fused features are estimated by proposing a novel constraint penalized cost function. The estimated fused features are used for the purpose of mapping. The classification accuracies obtained by applying a random forest classifier on the fused data confirm considerable improvements compared with the other methods used in the experiments.

Traditional exploration techniques usually rely on extensive geological field work complemented by geophysical ground surveying. However, this approach can be limited by field accessibility, financial status, area size and climate and can be confronted with public rebuff. We recommend the use of multi-scale hyperspectral remote sensing to mitigate the limitations of traditional exploration. Multi-scale remote sensing is particularly beneficial, especially in inaccessible and remote areas with little infrastructure, because it allows for a systematic, dense and generally non-invasive surveying. Additionally, Unmanned Aerial Systems (UAS) coupled with various sensors provide an opportunity to conduct noninvasive exploration in socially sensitive areas and in relatively inaccessible locations. The development of operational technologies and the evaluation of appropriate processing techniques in different mineral deposit environments contribute to a rapidly evolving field at the cutting edge of exploration technologies. Ultimately, this study provides the opportunity to advance the discovery of critical raw material deposits.

Hyperspectral scanners are increasingly being used in the mining industry as a non-destructive and non-invasive technique to efficiently map minerals in drill core samples. Hyperspectral data allows the characterization of different mineral assemblages, structural features and alteration patterns based on reflectance spectrum profiles. Traditional methods to analysis drill core hyperspectral data include the use of reference spectral libraries by visual analysis or a well established software. However, although these approaches produce good results, they are time-consuming and prone to errors. Therefore, in this paper, we take advantage of the latest and advanced machine learning techniques proposed in different scientific fields and explore the use of extreme learning machines (ELM) to map minerals in drill core hyperspectral data. This is a supervised technique that provides fast and automatic means to characterize hyperspectral data. To be able to implement this technique, a reference map was generated from the drill core hyperspectral data. The obtained results indicate that ELM can successfully map minerals in drill core hyperspectral data producing better quantitative and qualitative results than a typical RF classifier.

The increased availability of active and passive data captured over the same scene of interest makes it desirable to jointly utilize multisensor data to perform accurate classification. This paper proposes a novel fusion approach to integrate hyperspectral and LiDAR-derived digital surface model for land-cover classification. In this context, we propose a novel multisensor composite kernel technique based on extreme learning machines (named as multisensor composite kernels (MCKs)), which is capable of combining different methods in the feature fusion level in an effective way. In the proposed approach, we use extinction profiles to extract spatial and elevation features of hyperspectral and LiDAR data. Then, hyperspectral Stein's unbiased risk estimator (HySURE) is applied to identify the subspace (informative features) of spectral, spatial, and elevation features. Finally, MCK is applied to the extracted spectral, spatial, and elevation features to produce the final classification map. Results obtained by the proposed approach reveal the fact that this approach can effectively fuse and classify hyperspectral and LiDAR images and improve the classification accuracy of each data source significantly. In addition, the proposed method is fully automatic.

We propose to develop an efficient and integrated exploration workflow that includes remote sensing data obtained by multiple types of sensors at different altitudes, a combination that has been identified as potentially disruptive technology for the mineral exploration sector. The fusion of multi-source and multi-temporal data is, therefore, a key challenge for a successful data integration. Ultimately, the objective is to boost the competitiveness, growth, sustainability, and attractiveness of the raw material sector.

In this paper, we propose a supervised learning method for estimating mineral quantities in drill core hyperspectral data. Our proposed method links the high-resolution mineralogical analyses and hyperspectral data to learn a dictionary. The learned dictionary is then used for linear unmixing and estimating mineral abundances of the entire drill core sample. To evaluate the performance of the proposed method, we use a drill core data set, which is composed of the VNIR-SWIR hyperspectral data and high-resolution mineralogical analyses performed by a Scanning Electron Microscopy (SEM) instrument equipped with the Mineral Liberation Analysis (MLA) software. The quantitative and qualitative analysis of the experimental results shows that the proposed method provides reliable mineral quantity estimates.

In this paper, we propose a framework to fuse features extracted from hyperspectral and Light Detection And Ranging (LiDAR)-derived data. Spatial and elevation features are extracted from multisensor data using extinction profiles (EP). All the features, including the spectral ones, are fused using sparse and smooth low-rank analysis (SSLRA). In terms of classification accuracy, the proposed framework outperforms other studied fusion techniques used in the experiments.

The high demand for raw materials in our post-industrial societies contrasts the increasing difficulties to find new mineral deposits. In Europe, accessible and high-grade deposits are mostly exhausted or currently mined. Hence, future exploration must focus on the remaining, more remote locations or penetrate much deeper into the Earth's crust. Sustaining mining activities in Europe would allow the development of key technologies but also sustainable and ethical production of technological metals. Thus, we suggest to focus research on advances in multi-scale and multi-sensor remote sensing-based Earth integration techniques. The scale should range from satellite to air- and drone-borne systems and include ground validation. Multi-sensor downscaling methods involving SAR and optical data are particularly promising. We demonstrate that the integration with other sensors and/or measures such as geophysical/geochemical data as well as non-conventional remote sensing features such as textures and geometries are of interest. Thus, ultimately, our objective is to boost the competitiveness, growth, sustainability and attractiveness of the raw material sector in Europe. While we focus on the raw material sector as it is currently of strategic importance, the required methods are transferable to most environmental studies.

Exploiting multiple complementary classifiers in an ensemble framework has shown to be effective for improving hyperspectral image classification results, specially when the training samples are limited. With a different principle and based on this assumption that hyperspectal feature vectors effectively lie in a low-dimensional subspace, the subspace-based techniques have shown great classification performance. In this work, we propose a new ensemble method for accurate classification of hyperspectral images, which exploits the concept of subspace projection. For this purpose, we extend the subspace multinomial logistic regression classifier (MLRsub) to learn from multiple random subspaces for each class. More specifically, we impose diversity in constructing MLRsub by randomly selecting bootstrap samples from the training set and subsets of the original hyperspectral feature space, which lead to generate different class subspace features. Experimental results, conducted on two real hyperspectral data sets, indicate that the proposed method provides significant classification results in comparison with other state-of-the-art approaches.

Hyperspectral long-wave infrared imaging (LWIR HSI) adds a promising complement to visible, near infrared, and shortwave infrared (VNIR and SWIR) HSI data in the field of mineral mapping. It enables characterization of rock-forming minerals such as silicates and carbonates, which show no detectable or extremely weak features in VNIR and SWIR In the last decades, there has been a steady increase of publications on satellite, aerial, and laboratory LWIR data. However, the application of LWIR HSI for ground-based, close-range remote sensing of vertical geological outcrops is sparsely researched and will be the focus of the current study. We present a workflow for acquisition, mosaicking, and radiometric correction of LWIR HSI data. We demonstrate the applicability of this workflow using a case study from a gravel quarry in Germany. Library spectra are used for spectral unmixing and mapping of the main lithological units, which are validated using sample X-ray diffraction (XRD) and thin section analysis as well as FTIR point spectrometer data.

For vein hosted mineralization such as encountered in porphyry systems, the documentation of the main alteration assemblages associated with specific vein generations is essential in understanding the geometry of the mineralized body. Hence, mineralogical and structural information are highly relevant for characterizing the system. In this paper, we present an approach for the extraction of both mineralogical and structural information from hyperspectral scans. We propose a parallel framework which includes a typical mineral mapping technique for the extraction of mineralogical information as well as a ridge detection method, for the extraction of veins, applied on mineral abundance maps. In the proposed framework, the abundance maps are obtained from hyperspectral VNIR-SWIR drill-core scans using a linear spectral unmixing technique. Drill cores hosting porphyry stockwork type mineralization are used for the evaluation of the proposed technique and the experimental results show that the method offers a tool for accurately characterizing the mineralized body.

The classification accuracy of remote sensing data can be increased by integrating ancillary data provided by multisource acquisition of the same scene. We propose to merge the spectral and spatial content of hyperspectral images (HSIs) with elevation information from light detection and ranging (LiDAR) measurements. In this paper, we propose to fuse the data sets using orthogonal total variation component analysis (OTVCA). Extinction profiles are used to automatically extract spatial and elevation information from HSI and rasterized LiDAR features. The extracted spatial and elevation information is then fused with spectral information using the OTVCA-based feature fusion method to produce the final classification map. The extracted features have high dimension, and therefore OTVCA estimates the fused features in a lower dimensional space. OTVCA also promotes piece-wise smoothness while maintaining the spatial structures. Both attributes are important to provide homogeneous regions in the final classification maps. We benchmark the proposed approach (OTVCA-fusion) with an urban data set captured over an urban area in Houston/USA and a rural region acquired in Trento/Italy. In the experiments, OTVCA-fusion is evaluated using random forest and support vector machine classifiers. Our experiments demonstrate the ability of OTVCA-fusion to produce accurate classification maps while using fewer features compared with other approaches investigated in this paper.

According to the change-point analysis, 800 (= 61.6%) GIMMS series show at least 1 significant change in their annually integrated NDVI. Among these series 121 show more than 1 change. If a series encloses a change, its most significant one is linked to a shift of 5.5% of its 24-year mean on average. This underpins the need for including such non-linear aspects in the framework of trend analysis for vegetation dynamics in the Inland Delta. The spatial distribution of changes illustrates Fig. 2. About 28% of the changes appear from 1992/93 to 1993/94 and about 15% from 1986/87 and 1987/88 each. While the shifts from 1992/93 show up at the southern part, the earlier shits are located in the central and northern part of the Inland Delta.

Erosion in active mountain belts is one of the key questions in geomorphology. Remote sensing can be a powerful tool to predict erosion on a quantitative scale and helps to understand the near-surface processes involved. One of the major limits in these kinds of environments is the lack of ground truth information and its inaccessibility. Here we present an integrated approach in order to validate remote sensing applications with on-site information in small catchments. Image classification (MLC) on SPOT-5 data is applied to map land-use and relate it spatially with typical erosion rates. Precipitation measurements from the Tropical Rain Measuring Mission (TRMM) are compared with real precipitations from a rain gauge network. Denudation rates derived from land-use classifications (soil erosion) are related to absolute denudation rates calculated from suspended sediment concentrations. Our results outline the intricacy of competing processes in active mountain environments and that it is possible to measure spatial erosion from remote sensing information. Nevertheless, the spatial resolution, especially of TRMM data is limiting the small-scale erosion prediction.

The Main Ethiopian Rift (MER) which is characterized by large elevation differences and occurrence of Precambrian basement rocks and post-Miocene volcanic rocks is severely affected by wide gullies and dynamically expanding into agricultural lands at an alarming rate. We study the potential contribution of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data and drainage network analysis to discern the gully erosion in the main Ethiopian rift. A maximum likelihood classification (MLC) with two classes, gullies and non-gullies, is used to extract different shapes and patterns of gullies. The drainage network analysis of SRTM and ASTER DEMs is used to describe the geometry of the gullies and their linkage with the drainage system. Two study areas are selected for this purpose. The accuracy assessment yielded two different results (89% and 77% accuracy). The linkage of the classification results with drainage network showed higher density distribution of feeders linked with gullies class.

High topography and hardly accessible terrains make field studies on a large-scale cumbersome. An integrative approach, employing several remote sensing techniques combined with field studies, as well as experimental and numeric simulations, provides tools for the understanding of coupled processes. New remote sensing technologies have the capability of measuring physical parameters, such as precipitation, land use, vegetation coverage, soil moisture, and uplift with an area-wide coverage and high spatial resolution. These techniques allow us to quantify the surface deformation (intensity, timing, localization) and the influence of environmental processes such as surface and underground water flow, seismic and landslide hazard, and, to some extent, land use. The final aim consists to generate a suite of tools allowing the quantification of surface processes at the interface between tecto-, hydro- and atmosphere, mainly using remote sensing data.

This study examines the land cover changes that occurred in the catchment of Awassa between 1986 and 2006 in order to evaluate the importance of urban growth and deforestation in the context of lake level rise and increasing discharge values. The study is based on a LANDSAT scene acquired on January 21, 1986 and a ASTER scene acquired on January 27, 2006. By doing so, two independent maximum likelihood classifications were performed. Consequently, a difference map was calculated and spectral changes were evaluated using the IR_MAD transformation. Results show that urban growth and deforestation occurred but there is no proof that these processes took place on a large scale and that they are significantly influencing the discharge patterns. Nevertheless, the change detection map created on the basis of IR-MAD indicates that the difference map based on the individual classifications does not account for the deforestation processes that occurred in the eastern part of the catchment in a sufficient amount.

In this paper, we propose to use drainage pattern in order to characterize neotectonic deformation. We test several methods that can be used to examine a drainage system in map view, the watershed basin and its relations to the river draining it. If equilibrium state is given the axial symmetry of the basin should be the flow path of the main river. We therefore explore the link between stream patterns and watershed basins with the concept of medial axis transform (MAT). Additionally the basin shape was explored using GIS. These data supplements basin asymmetry vectors and ancient watersheds derived from filtered DEM. Altogether quantitative analysis of watershed divides and streams are a useful tool to gather information about neotectonic folding and faulting.

Earth's changing surface reflects a dynamic linkage between various internal and surface processes. The aim of this ongoing project is to quantify erosion based on morphology combined with climatological data (precipitation) in a tectonically and climatologically very active area. This study is carried out as a consequence of good results in previous works, using both: empirical and deterministic approaches by means of remote sensing data. First: the empirical attempt, the Revised Universal Soil Loss Equation (RUSLE) with its ability to operate on various, from catchment to area, scales. This approach delivers a good idea about soil erosion, especially when focusing on the sensitivity of soil loss, but not taking big mass transports, like in landslides or by rivers, into account. Second, there is the river profile analysis carried out for various streams individually. This attempt is detachment limited and will not give an accurate idea about what is going on beyond the considered catchment. We want to combine both attempts in one equation to use the strengths of each approach and improve our previous results for a large study area but with comparable fine-resolution. This study should make a contribution to the understanding of the correlation between climatic factors, tectonics, soil erosion and river incision. In contrast to former research we want to create a comprehensive model describing all these relationships only on the basis of remote sensing data. Our model is not limited to the presented study area but applicable anywhere where erosion takes place.

In this study we examine the classification accuracy of a CHRIS (Compact High Resolution Imaging Spectrometer) data, acquired on May 18, 2004 (monsoon). The test site is a typical peat swamp landscape located in South Borneo (Central Kalimantan, Indonesia). We focus on eight specific land use/cover categories from a single view angle (at nadir as a reference) and from a multi-angular perspective in four view angles with 18 spectral bands. We show that (1) the reflectance increases accordingly to the successional stages for a given angle and (2) that reflectance values increase in the near-infrared with decreasing leaf area index (LAI). From the single (nadir) to the multi-angular approach, classification overall accuracy increased from 77.1% to 90.4%. Kappa statistics increased from 0.74 to 0.89 and confirmed that the classification performances were statistically different at a 5% level of significance. Our results demonstrate that multi-angular data improve the differentiation between different Peatland landscape classes.

The Hindukush region in north-western Pakistan is amongst the most active geomorphic regions in the world and is bounded by principal active zones. This study focuses on the application of remote sensing techniques in order to show the spatial variation of uplift and deformation along the Tirch Mir Massif and Shyok suture zone in the eastern Hindukush. Stream profile analysis and box counting techniques were employed on drainage network extracted from digital elevation model (DEM) to calculate the geomorphic indices and fractal dimension. The estimation of fractal dimensions allows us to measure the degree of complexity by evaluating how the dimension measurement increases or decreases at different scales with respect to the vulnerability of the surface deformation (surface roughness). The objective is to quantify the influence of neotectonic activity on the drainage system by measuring the reduction in complexity as the deformation intensity increases. We used a steepness index map to prepare a relative uplift rate map of the area. It is also observed that the main control over the drainage system is tectonic uplift. Quaternary faults in the region control local drainages and the deflection of rivers and stream offsets is a further evidence of neotectonic activity. This study can be improved by using high resolution imagery and GPS data. The anomalous and heterogeneous behaviour of drainage pattern, seismicity and fractal dimension values also prove the active nature of the Hindukush region.

The Nanga Parbat Haramosh Massif (NPHM) is an active tectonic feature of the north-western Himalayas. The recent seismic activity lies on an active seismic zone between Sassi and Raikot, from north to south, and is called Raikot-Sassi fault zone. The drainage pattern of NPHM is disconnected at different location especially along the active Raikot-Sassi fault zone. The stream profile analysis of Indus River in the massif revealed four different locations of the active faults. The spatial distribution of geomorphic indices suggests that the western portion of the massif is more deformed compared to any other location. We observed variable relative uplift rates ranging from 7-13 mm yr-1in different locations with higher rates in the area along Raikot fault. The focal mechanism solutions (FMS) of recent events suggests that these active faults are strike slip with major thrust components. The correlation dimension values suggests that the events have failed to fill up the plane in the source zone. The heterogeneous drainage pattern, stream profile analysis and seismological characteristics suggest that the Raikot Fault zone is highly deformed and relates to strike slip dominated thrusting.

This work demonstrates the utility of reduced resolution ALOS PALSAR data for biomass mapping and land cover classification over the tropical forests of Indonesia. This study is important because we processed the ALOS PALSAR mosaic, which is made freely available within K&C initiatives project and will be updated regularly. We first used 38 sample plots collected on the ground during dry season in September 2004, to develop a tree diameter (dbh)-biomass model. The HH, HV, HV/HH and HH-HV backscatters of ALOS PALSAR data allowed the empirical estimation of forest above ground biomass (AGB). Each band of PALSAR data was separately used to estimate the biomass, and we found HV band resulted in better correlation with the AGB compared to other SAR bands. Validation of the prediction results was carried out by comparing the biomass estimates with those predicted from an existing allometric equation. Optical data are sensitive to the physical properties of the reflectors whereas SAR data are more influenced by the geometric properties of the scatterers. Therefore, the second part of this study concerned the integration of mosaic SAR textures and ETM data for land cover classification. The classification was conducted using ETM data and variations of ETM, SAR bands, and SAR textures calculated using GLC Matrix. The image classifications were carried out using a Machine Learning based classifier, so-called Support Vector Machine (SVM), and a conventional Maximum Likelihood method. An ensemble of neural networks method using Kalman filter and scaled conjugate gradient algorithm was applied. The classification accuracy was assessed using confusion matrices and Kappa statistics. We show that the introduction of SAR textures significantly enhanced the classification accuracies. This study showed that the joint processing of SAR and multispectral data increased the accuracies of biomass estimation and landuse classifications. The efficiency of the method at medium spatial resolutions allows its application of global datasets.

In this paper we show that a quantitative analysis of remote sensing data allows the localization of active deformation and the quantification of strain intensity and kinematics. As tectonics controls topography, which in turn constrains river patterns, the procedure is based on the calculation of nonlinear morphometric parameters describing the disequilibrium of rivers. Thus the meandricity and the dendricity of rivers are estimated by fractal analysis. Structural control on river paths is quantified by correlation and covariance analyses. Terrain uplifts are quantified by stream power approach. These parameters are a valuable addition to existing methods especially wheninsitumeasurements are scarce.

Earth systems operate over very diverse spatial and temporal scales. It requires application of a wide range of specialized technologies to measure and model their interrelation. This study is focused on the estimation and final calculation of erosion rates based on the interactions of climate factors with topography for the whole Tibetan plateau, by means of remote sensing data. The complex interrelationship among natural factors (precipitation, soil texture, topography, vegetation) and human activities (cultivation management), combined with the large area, unique geomorphological features and the lack of available long term data sets, as well as the hardly accessible terrain are an outstanding challenge for the investigation of this area. This ongoing project has a twofold outcome: to better understand the relationship between mountain and plateau building with climatic factors on the one hand and erosion on the other, and also to produce a precise erosion risk map for the region which is observed in this study.

Digital elevation models (DEMs) are key component for computer-based analyses of river profiles, drainage basin as it provides elevation information for the land surface throughout the catchment of the area. During the Cenozoic uplift of Tibetan plateau and surrounding ranges due to India-Eurasia collision, the tectonic processes are interacting with the local random effects (e.g. Landslides, Glaciations and climatic Changes) and are linked with the development of a unique river network in this region. These rivers have distinct patterns and are controlled by different tectonic and climatic regions. Drainage history of the Pamir is related to continental movements of the plates, displacements of the tectonics, regional uplift and erosion of various individual tectonic units. This study focuses on the application of remote sensing techniques in order to show the spatial variation of uplift and deformation along the right bank tributaries of Pyanj (Vanch, Yazgulem, Aksu-Murghab-Bartang, Gunt-Alichur and Shokhdara) and one of the few left bank tributary (Shiveh river) and Pyanj itself. DEM data is used to extract river network in this area. Moreover, slopes and drainage areas are also calculated from Digital Elevation Model. Based on the stream power law, we make area-slope plot so as to derive channel parameters like concavity (thetas) and steepness (Ks) which are related closely to uplift and deformation. The lineaments and major tectonic features have been digitized from geological maps of the region. The uplift, steepness and hack index maps have been generated by using some specially designed algorithms for this purpose.

This work implemented a soft classification of neural network using Kalman filter algorithm (KFNN) for complex land cover mapping. Back propagation neural network (BPNN), SVM and maximum likelihood (MLC) were applied as comparisons. Using `hard' and `fuzzy' confusion matrices, the classifications were assessed. The KFNN outperformed other classifiers in terms of overall accuracy and Kappa statistics. Shannon Entropy and Confusion Index (CI) were estimated, and we found the uncertainty of classified pixels over the study area is relatively low as their membership values are not distributed evenly.

This project aimed to generate a geological map and structural study of the Zagros Mountains for oil exploration purpose. The study area contains portions of the simply folded belt, main Zagros thrust (MZT) and portions of the complex hangingwall of the MZT. We merged the information acquired from quantitative remote sensing analysis and from analogue models in order to produce 3D models of the geological object. A direct assessment of the results is possible by comparison with models obtained by an independent geophysical survey.

Remote sensing is a significant tool to process the geological structures located in the zones with low vegetation and good exposures. In this paper we use statistical analysis of remote sensing data to model the process of folding in the SE of ZAGROS. The ZAGROS simply folded belt comprises a gently folded cover sequence which has been detached from the underlying basement along the Hormoz evaporates and is locally disrupted by recent faults. We used mosaic of 14 landsat ETM+ scenes that covers this region. We digitized 515 hinge lines of synclines and anticlines and measured their lengths. We show that the fold length distribution is fractal. The fractal analysis has 2 implications. First it allows the quantification of the complexity of the geological surface deformation. This complexity arises from growth, interaction and connection of folds to form networks. Secondly, it permits to model the development of folds. We propose that the fault network is an Iterated Function System (IFS). Such a model allows us to understand the structural evolution of a compressional range in 4 dimensions, the fourth dimension being time.

While the Tropical Andes are considered as the hotspot of biodiversity, in terms of endemic species, Ecuador is subject to South Americas second highest deforestation rate. The need for retaliatory action calls for cost-effective monitoring of land use changes in extensive and often inaccessible areas. We present a change-detection method designed for the requirements of a tropical mountain rainforest ecosystem and investigate, how the spatial distribution of deforestation links to infrastructure.

Geochronological dating with the fission-track method is based on time-consuming counts of the spontaneous and induced tracks. Automatic extraction and identification of tracks would not only improve the speed of track counting but also eliminate variation due to the observer. Pixel values alone are not enough to distinguish between tracks and background. Traditional pixel-based approaches are therefore inefficient for fission track counting. Image analysis based on objects, which include shape, texture and context information is a more promising method.

Object-based classification is a rapidly developing paradigm in image analysis. Unlike pixel-based techniques which only use the layer values, the object-based techniques can also use shape and context information of a scene texture, thereby offering more degrees of freedom in image analysis. The first and important step of an object-based classification system is the segmentation of the image in to primitive objects. Various segmentation algorithms have already been developed to serve this purpose each of them having its own set of limitations. In this article, we present a new algorithm for image segmentation based on identifying natural clusters. This new algorithm is not the perfect solution to handle various segmentation problems. However, in some cases it is proven to be efficient.

The use of remotely sensed data for the classification of forest cover has been effectively proven by means of multi- source remotely sensed data. This study concerns on two forest sites in Southern Ecuador and Central Indonesia. Support vector machine classification is applied on both sites, elaborating texture data as additional information to improve classification accuracy. Two types of texture data, which are estimated using grey level co-occurrence matrix (GLCM) and geostatistics methods, were applied by means of moving window. The result showed that the performance of the SVM had notably improved when texture data used with spectral data for mapping of forest cover.

The thrusting of the Cuban Oriente block onto the Bahamas platform and the transform movement between the Caribbean and North American plate cause oscillating uplift in the east of Cuba, manifesting itself in tilted blocks, coral reef terraces and rivers cutting deep into the bedrock. Objectives of this work are to identify active tectonic boundaries and derive relative uplift rates in Oriente using power-law scaling relation between channel slope and contributing drainage area to obtain a more detailed picture of the tectonic processes of the study area. Geomorphological interpretation and analysis of river profiles shows an inhomogeneous distribution of relative uplift rates within the Cuban Oriente block. This method allows for the estimation of deformation over large areas, the localization and the quantification of vertical displacements.