This study delves into the agricultural landscape of Bahia, Brazil, employing the Mask R-CNN deep learning model with satellite imagery to detect three crop growth stages (early, mid-growth and maturity stage). This model is suited to the region’s complex terrain and diverse crop patterns, providing accurate instance segmentation crucial for monitoring crop development. Remarkable results have been achieved with a limited dataset of just 54 images for training, underscoring the model’s efficiency in scenarios where extensive data collection is challenging. The validation metric chosen for this study is the Intersection over Union (IoU), preferred for its ability to quantify the pixel-wise overlap between the predicted and actual segmentations, offering a clear measure of accuracy in spatial contexts. An IoU of 90% was obtained, demonstrating Mask R-CNN’s robustness and potential for precision agriculture in challenging environments.

Wildfires in the Brazilian Amazon have raised significant concerns owing to the environmental, social, and global impacts associated with these events. They have led to habitat loss for various species and release of substantial amounts of carbon dioxide into the atmosphere. Thereby contributing to climate change and deterioration of air quality due to pollutants emission. The integration of advanced technologies, including high-spatial resolution satellite data and image processing algorithms, enables a more precise and comprehensive understanding of the wildfire scenario. This research introduces a model based on deep learning that can be applied over Sentinel-2 images to reliably detect fire scars with an accuracy above 90% (92% on training data and 82% on validation data). A SpectrumNet convolutional neural network was employed, incorporating features extracted from spectral bands at 10m and 20m.

Accurate detection of clouds and shadows present in optical imagery is important in remote sensing for ensuring data quality and reliability. This study introduces a deep learning model capable of generating precise cloud and shadows masks for subsequent filtering. Unlike other works in literature, this model operates efficiently across diverse temporalities, sensors, and spatial resolutions, without the need for any relative or absolute transformation of the original data. This versatility, to date unreported in the literature, marks a significant advancement in the field. The model utilizes data from PlanetScope, Landsat and Sentinel-2 sensors and is based on a simplified convolutional neural network (CNN) architecture, LeNet, which facilitates easy training on standard computers with minimal time requirements. Despite its simplicity, the model demonstrates robustness, achieving accuracy metrics over 96% in validation data. These results show the model potential in transforming cloud and shadow detection in remote sensing, combining ease of use with high accuracy.

This paper presents an analysis of two inland water bodies, Salvajina Reservoir and Sonso’s lagoon, located in the Upper Cauca River Basin, Colombia. Such analysis is carried out in the context of Water Security (WS) by considering their inherent problems to be monitored in a permanent manner (i.e., difficult access, insecurity) and taking advantage of Remote Sensing (RS) platforms. To do so, temporal mapping was done by: (i) automatically segmenting the inland water bodies; (ii) applying the Case 2 Regional Coast Color (C2RCC) algorithm to obtain an approximation to water quality parameters (e.g., chl-a, TSM); (iii) extracting statistical information such as area variation, radiometric index values, and mean values in parameters of water quality; and (iv) providing relevant information for decision makers in the context of WS. The analysis was done over Landsat-8 and Sentinel-2 images between 2014-2021 and 2020-2021, respectively. Planet images were used to validate the segmentation results.

High-resolution (HR) satellite image time series (SITS) are a valuable data source for analyzing land cover change (LCC) due to their large amount of spatial, spectral, and temporal information. However, most existing LCC detection methods focus on binary change detection (CD) within a single year and fail to provide detailed information about the specific type of change. In this study, we propose a multiannual CD approach that identifies changes occurring between consecutive years and provides information about the type of LC transition. The proposed approach exploits multiannual and multispectral SITS to generate a hypertemporal feature space (FS). This FS is analyzed to create a set of CD maps that indicate the time, probability, and type of change. To measure the similarity between pixel time series, we use dynamic time warping (DTW) in the space of hypertemporal features. A hierarchical clustering technique is exploited to develop a set of class prototypes (CPs) that represent the characteristics of different LC classes. The CPs are then used to identify the most probable LC transition for each changed pixel. Two test areas were selected to evaluate the effectiveness of the proposed approach. The first one is located in Amazon and spans the years 2015 to 2019; and the second one is located in Sahel-Africa and covers the years 2015 and 2016, using multiannual Landsat 7 and 8 SITS. The results demonstrate that the proposed approach is effective in detecting multiannual changes and in identifying the LC transitions.

Biomass estimation is a crucial component in the areas of carbon storage and forest management. Biomass can be analyzed rather at forest or at Single Tree Level (STL) and studies in both directions can be found in literature. Nevertheless, working at STL provides more accurate estimations. Such a level of information can be obtained by means of LiDAR data, but this type of data is usually expensive and not available for all Countries. Thus, few studies at STL can be found in developing countries and tropical forests. This study presents one of the first works for biomass estimation in tropical forest located in Gorgona Island, Colombia. Adaptations have been made to state-of-the-art methods for them to properly work in a complex forest, where trees sizes vary a lot from one area to another. Preliminary results are shown for some areas, allowing to see the capabilities of the adaptation.

Wind disturbances represent a great source of damage in forests, and an assessment of such damage is very important for adequate forest management. Remote sensing is an effective tool for this purpose and can be used by considering different data sources: active vs passive sensors. While passive sensors can provide a direct view of windthrows, they are often affected by clouds. Active sensors have the significant advantage of not being affected by the presence of clouds which can be prevalent in certain seasons in mountain areas. The objective of this study is to compare the capability of active (Cosmo SkyMed SAR sensor) and passive (Sentinel-2 and Planet sensors) data in detecting windthrows in different seasons of image acquisition. A study site was analysed, located in the Trentino-South Tyrol region (Italy), which was affected by the Vaia storm on 27-30 October 2018, which caused significant forest damage.

Mapping waterbodies variations through time is only possible thanks to the use of in-situ hydrometric sensors or remotely sensed data. Few areas around the world count with a functional in-situ sensor’s network, but all areas can be observed with satellite imagery. Several previous studies have mapped waterbodies by means of optical satellite imagery. Combining both optical and radar data is an alternative to avoid high cloud coverage or low data availability. This work presents a workflow for mapping waterbodies variations of lakes, spatially and temporally, located in the Central Rift Valley, Ethiopia by considering Landsat-based analysis-ready data alongside Sentinel-1/2 imagery, and comparing automatic thresholding methods. The workflow is simple, yet effective, and makes use of the Digital Earth Africa Open Data Cube, for the very first time in Ethiopia to accelerate time-series processing with the potential to extend this analysis to a national scale, addressing water security challenges.

To overcome the limited capability of most state-of-the-art change detection (CD) methods in modeling spatial context of multispectral high spatial resolution (HR) images and exploiting all spectral bands jointly, this letter presents a novel unsupervised deep-learning-based CD method that can effectively model contextual information and handle the large number of bands in multispectral HR images. This is achieved by exploiting all spectral bands after grouping them into spectral-dedicated band groups. To eliminate the necessity of multitemporal training data, the proposed method exploits a data set targeted for image classification to train spectral-dedicated Auxiliary Classifier Generative Adversarial Networks (ACGANs). They are used to obtain pixelwise deep change hypervector from multitemporal images. Each feature in deep change hypervector is analyzed based on the magnitude to identify changed pixels. An ensemble decision fusion strategy is used to combine change information from different features. Experimental results on the urban, Alpine, and agricultural Sentinel-2 data sets confirm the effectiveness of the proposed method.

This paper presents an approach for large-scale precise mapping of agricultural fields based on the analysis of Satellite Image Time Series (SITS) acquired by ESA Sentinel-2 (S2) satellite constellation. The approach has been developed in the framework of the ESA SEOM - Scientific Exploitation of Operational Missions - S2-4Sci Land and Water project. The goal is to design a flexible and automatic processing chain able to perform mapping in massive data. Here we focus on precision agriculture products generation at country level. In particular, the Country of study is Italy and the application goal is precision agriculture of single crop fields. To achieve this goal, two macro challenges are considered: (i) download and pre-processing of S2 SITS, and (ii) multi-temporal (MT) fine characterization of agricultural fields. Both challenges are addressed in an automatic way by exploiting and/or updating state-of-the-art methodologies. Promising results have been obtained over years 2017 and 2018 for Italy.

Satellite image time series (SITS), such as those by Sentinel-2 (S2) satellites, provides a large amount of information due to their combined temporal, spatial, and spectral resolutions. The high revisit frequency and spatial resolution of S2 result in: 1) increase in the probability of acquiring cloud-free images and 2) availability of detailed information for analyzing small objects. These characteristics are of interest in precision agriculture, where temporally dense SITS can benefit the understanding of crop behaviors. In the past, information about agricultural practices has been collected over large regions and focused on mixed/aggregated crops due to the poor tradeoff between the spatial and temporal resolutions. Products have been generated at low spatial resolution and daily basis or at high spatial resolution and weekly/monthly basis. They are meaningful for large agricultural fields, whereas they are limited when fields show a small average size. In this context, S2 characteristics allow for both high spatial and temporal resolution products. However, no existing automatic method effectively separates small fields from each other in an unsupervised way and deals with data irregularly sampled in time. Thus, this article presents a method suitable for the analysis of small crop fields in S2 dense SITS that accounts for S2 characteristics. The method fuses spatio-temporal information, analyzes data spatio-temporal evolution, and extracts relevant spatio-temporal information. The effectiveness of the proposed method was corroborated by experiments carried out on S2-SITS acquired over an area located in Barrax, Spain.

Crop-type classification has been attracting a lot of attention in recent years. In particular since the launch of the Sentinel-2 (S2) satellite which combines a large amount of spectral and spatial information, compared to previous satellite generations. In the literature, several methods exist that perform crop classification in time series, but most of them: i) work at pixel level; ii) perform single-data analysis; and/or iii) consider a single feature. This results in low performance of state-of-the-art methods. This paper presents an approach that works at object-level and exploits both spatial and temporal information coded in NDVI time series and phenological parameters and takes advantage of a semi-supervised paradigm by combining a new hierarchical correlation clustering with an artificial neural network. The effectiveness of the proposed approach was corroborated over an intensive cultivated area located in Barrax, Spain. Crop-type classification was compared to state-of-the-art methods.

One of the most common approaches to unsupervised change detection (CD) in multispectral images is change vector analysis (CVA). CVA computes the multispectral difference image and exploits its statistical distribution in (hyper-) spherical coordinates by means of two steps: 1) magnitude and 2) direction thresholding. The two steps require assumptions on: 1) the model of class distributions and 2) the number of changes. However, both assumptions are seldom satisfied or difficult to formulate, especially when considering VHR images. Thus, we propose an approach to multiple CD in VHR optical images based on iterative clustering and adaptive thresholding in (hyper-) spherical coordinate. The proposed approach: 1) is distribution free; 2) is unsupervised; 3) automatically identifies the number of changes; and 4) is robust to noise. Results obtained on two multitemporal single-sensor and multisensor data sets, including images from WorldView-2 and QuickBird, corroborate the effectiveness of the proposed approach.

The availability of multitemporal images acquired by several very high geometrical resolution (VHR) optical sensors makes it possible to build VHR image time series (TS) of images acquired over the same geographical area with a temporal resolution better than the one achievable when considering a single VHR sensor. However, such TS include images showing different characteristics from the geometrical, radiometrical, and spectral viewpoint. Thus, there is a need of methods for building homogeneous VHR optical TS when using multispectral multisensor images. By focusing on the spectral domain, we propose a method to transform a VHR image into the spectral domain of another image in the same multisensor TS but acquired by a different sensor. To this end, a prediction-based approach relying on a nonparametric regression method is employed to mitigate sensor-dependent spectral differences. The impact of possible changes occurred on the ground is mitigated by training the prediction model on unchanged samples, only. Experimental results obtained on VHR optical multisensor images confirm the effectiveness of the proposed approach.

Satellite Image Time Series (SITS), such as the ones acquired by the new Sentinel-2 (S2), combine a large amount of information compared to previous satellite generations since a better trade-off in terms of spatial/spectral/temporal resolutions is guaranteed. The specific characteristic of acquiring images under overlapped orbits, offered by S2, results in: i) availability of irregularly sampled acquisitions and ii) increase of the probability to acquire cloud free images over time. This characteristic becomes relevant in the agricultural analysis, where availability of dense SITS is required to map and analyze fast working crop behaviors. In the literature, several methods exist that extract phenological parameters for agricultural analysis, but none of them is able to deal with irregularly sampled data. Thus, this paper presents an approach for derivation of cropland phenological parameters from irregularly sampled S2-SITS. Experimental results obtained on S2-SITS acquired over Barrax, Spain, confirm the effectiveness of the proposed approach.

When dealing with optical images, the most common approach to unsupervised change detection is Change Vector Analysis (CVA) which computes the multispectral difference image and exploits its statistical distribution in (hyper-)spherical coordinates. The latter step usually requires assumptions on both the model of class distributions and the number of changes. However, both assumptions are seldom satisfied especially when multisensor VHR images are considered. Thus, we propose an approach to multiple change detection in multisensor VHR optical images based on iterative clustering in (hyper-) spherical coordinate. The proposed approach is distribution free, unsupervised and automatically identifies the number of changes. Results obtained on a multitemporal and multisensor dataset including images from WorldView-2 and QuickBird are promising.

The availability of multitemporal images acquired by several very high geometrical resolution (VHR) optical sensors makes it possible to build VHR image Time-Series (TS) with a temporal resolution better than the one achievable when considering a single sensor. However, such TS include images showing different characteristics from the geometrical, radiometrical and spectral viewpoint. Thus, there is a need of methods for building consistent VHR optical TS when using multispectral Multi-Sensor (MS) images. Here we focus on the spectral domain only, by designing a method to transform one image in an MS-TS into the spectral domain of another image in the same MS-TS, but acquired by a different sensor. To this end, a prediction-based approach relying on Artificial Neural Networks (ANN) is employed. In order to mitigate the impacts of possible changes occurred on the ground, the prediction model estimation is based on unchanged samples only. Experimental results obtained on VHR optical MS images confirm the effectiveness of the proposed approach.