Georeferencing and orthorectification of images plays a vital role in ensuring accurate and reliable geospatial data. They improve distance measurement precision, facilitate data integration and comparison, enhance geospatial analysis, and enable meaningful visualisation and interpretation of imagery. In this contribution, we describe the processing pipeline developed at Kuva Space to refine the georeferencing and orthorectification of PRISMA products using optical flow algorithms. The proposed method achieves subpixel accuracies and has the ability to run a full scene in under one second.

Over the past decade, Deep Learning (DL) models have proven to be efficient at classifying remotely sensed Earth Observation (EO) hyperspectral imaging (HSI) data. Those models show state-of-the-art performances across various bench-marked data sets by extracting abstract spatial-spectral features using 2D and 3D convolutions. However, the black-box nature of DL models hinders explanation, limits trust, and underscores the need for profound insights beyond raw performance metrics. In this contribution, we implement a simple yet powerful mechanism for the explainability of DL-based absorption features using an axiomatic approach called Integrated Gradients, and showcase how such an approach can be used to evaluate the relevance of a network’s decisions, and compare network sensitivities when trained using single and dual sensor data.

The high productivity of biomass registered in eutrophic water bodies, leads to qualitative and quantitative changes in the phytoplankton community, resulting in massive algae blooms. This research evaluates different atmospheric cor-rection methods, Sen2cor and Acolite, over Sentinel-2 (S2) images and its effects for monitoring algae blooms in an eu-trophic reservoir. Specifically, we analyze two dates com-paring the corrected reflectance to field reflectance data and laboratory results to study the turbid and productive water of San Roque reservoir, Argentina.

Oviposition measurement with ovitraps is one of the most widely used methods to monitor Aedes aegypti mosquito activity in the world. Egg counting is however very time consuming. This paper presents the semi -automatic counting of mosquito eggs laid on ovitrap sticks in images acquired by cellular phones. In Cordoba, Argentina, 150 ovitraps were distributed in the city to measure the evolution of the Aedes aegypti population, estimated indirectly by the number of laid eggs. An important increase in the counts is a potential indicator of an imminent outbreak, alerting the health services to warn the population and recall the good sanitary practices. Bringing image processing to this proj ect is a way to relieve the technician from the tedious egg counting behind a magnifier and to reduce the count errors due to distraction or fatigue. We developed a fast semiautomatic counting solution with tools to focus on the useful image area, to show the confidence of automatic count numbers and to handle the collection of results.

Remote sensing community is making enormous efforts to implement early warning systems capable for following spatio-temporal patterns of water quality and climate change risk indicators, being Horizon 2030 EOXPOSURE project one of them. This work presents first results of surface temperature Landsat 8 Level 2 Collection 2 products analysis for a reservoir and compare them with field data measurements. A Root Mean Square Error (RMSE) of 1.7°C and a Mean Absolute Percentage Error (MAPE) of 7% were obtained for these products but validation curve resulted not confident at a 95% level. A semiempirical linear model with 94% accuracy, RMSE of 1.1°C and a MAPE of 5% is presented. It was successfully validated with a control group data set obtaining 94% accuracy. A Water Surface Temperature temporal series is shown for the 2013–2020 period and spatio temporal patterns are analyzed and discussed. Water surface temperature behavior in zones with algal bloom occurrence present greater significant values, up to 3°C, than those with clearer water, indicating that water emissitiviy must be revised for these cases.

Mapping Human Exposure to Risky Environmental Conditions is key to quantify the vulnerability of population and economic assets. In order to develop novel tools, implementing the use of information layers from current and future Earth Observation (EO) missions is necessary. The EOxposure project that has been created and funded by the European Commission's Horizon 2020 research and innovation program covers this porpoise. Several topics involving human exposure to environmental risks are being studied, including water quality and pollution, which is addressed in this paper. The high productivity of biomass registered in eutrophic water bodies, leads to qualitative and quantitative changes in the phytoplankton community, resulting in massive algae blooms. This research work proposes a methodology that takes advantage of the temporal and spectral resolution of Sentinel-2 (S2) for monitoring eutrophic reservoir. Specifically, it uses large temporal series of S2 images and advanced data mining techniques to study the turbid and productive water of San Roque reservoir, Argentina. The spatial patterns and the temporal tendencies of these aquatic indicators are analysed and evaluated in order to assess their contribution to water quality models and a local water management program.

As part of a collaborative effort among researchers of several institutions and organizations, this project takes advantage of the Google Earth Engine (GEE) cloud computing environment to map algae bloom over the main water bodies and reservoirs of Latin America using Sentinel-2 imagery (2015 to present). The methodology based on the Normalized Difference Chlorophyll Index (NDCI) for chlorophyll-a and Trophic State Index (TSI) detection provided promising results. NDCI responds well to high levels of chlorophyll-a and, therefore, can be used as an indicator for algae blooms. The image processing as well as the display of maps and charts are being implemented into a GEE App to be freely available for general public use.

Extensive eutrophication process in water body may lead to the creation of algal blooms, reduction in oxygen supplies, death of aquatic life and danger to human health. Monitoring eutrophic processes is therefore mandatory to the aquatic environment and human health. However, the changes in the spatial and seasonal distribution of the phenomena are difficult to be resolved using sparse water sampling or acquisition of remote sensing data. Therefore, this research work proposes a methodology that takes advantage of the temporal and spectral resolution of Sentinel-2 (S2) for monitoring eutrophic reservoir. Specifically, it uses large temporal series of S2 images and advanced temporal unmixing model to study the spectral response of the turbid and productive water of San Roque reservoir, Argentina. The spatial patterns and the temporal tendencies of these aquatic indicators are analysed and evaluated in order to assess their contribution to the local water management.

Eutrophication is a process in which elevated organic matter and nutrients raises the primary production of a water body. As a result, the productivity of phytoplankton and biomass are very high at all trophic levels. During bloom event, the spatial and temporal distribution of this phenomena is difficult to be observed using conventional water sampling methods. This work advance the state of the art by using Sentinel-2 (S2) images to estimate chlorophyll-a (chl-a) concentration with an empirical model. Specifically, the model uses band 8 (NIR) and band 4 (red) to predict chl-a concentration during an algal bloom event in San Roque lake, Córdoba, Argentina. Nevertheless, novel spectral ratio for algae composition patterns has also been created using bands 8a and 9. The results show that S2 has the potential to monitor bloom events in eutrophic lakes.

Damage assessment, protection and preservation of built patrimony are a priority at national and local levels due to their importance to many cultural and economic aspects. This paper presents a methodology to estimate the potential damage caused by ground settlement for cultural heritage buildings using remotely sensed big data. Specifically, it presents a framework to assess the potential damage caused by ground settlement for masonry, infilled and bare frames structures using Persistent Scatterer Interferometric (PSI) measurements. The proposed solution advances the state-of-the-art by integrating big Earth observation (EO), environmental, architectural and historical data, for estimating the settlement induced damage to hundreds thousands of buildings. The fully automatic scheme was created within cloud computing environment for accelerating data transfer, processing and modeling and for improving the visualization of image-derived products.

As more and more geospatial data are produced, Big Earth data is becoming a new key to the understanding of the Earth. Such opportunity also comes with new issues and challenges related to the massive and heteregenous amount of data to process and to analyse. The present work explores the use of three types of Earth Observation (EO) data in order to automatically classify built and non-built areas in Africa using a machine learning classifier: SAR (Sentinel) and optical (Landsat) imagery, and the OpenStreetMap (OSM) database as training data. Experimental results in ten african cities show that the use of satellite data from multiple sensors improves the performance of the classifiers in these areas. They also show that using crowd-sourced geospatial databases such as OSM as training data leads to similar accuracies than when relying on field surveys or hand-digitalized datasets.

High resolution estimates of human population distributions are very useful for large-scale or national scale analyses in many fields including epidemiology, healthcare, resource distribution, and development. Population densities have long been estimated using remote sensing data, particularly at large spatial scales. However, the accuracy of population density predictions can be very poor in cities, and this is particularly relevant in urban areas in sub-Saharan Africa. Here we map intra-urban population densities for select African cities by disaggregating census data using random forest techniques with remotely-sensed and geospatial data, including bespoke time-series intra-urban built-up data. We produce maps with up to 83% explained variance and find including built-up density layers in urban population models allows for clear improvements in prediction.

In this letter, the recently developed extreme gradient boosting (Xgboost) classifier is implemented in a very high resolution (VHR) object-based urban land use-land cover application. In detail, we investigated the sensitivity of Xgboost to various sample sizes, as well as to feature selection (FS) by applying a standard technique, correlation-based FS. We compared Xgboost with benchmark classifiers such as random forest (RF) and support vector machines (SVMs). The methods are applied to VHR imagery of two sub-Saharan cities of Dakar and Ouagadougou and the village of Vaihingen, Germany. The results demonstrate that Xgboost parameterized with a Bayesian procedure, systematically outperformed RF and SVM, mainly in larger sample sizes.

Ground displacements that cause structural damage to heritage buildings are precipitating cultural and economic value losses. The GEPATAR project (GEotechnical and Patrimonial Archives Toolbox for ARchitectural conservation in Belgium) aims creating an online interactive geoinformation tool that allows the user to view and to be informed about the Belgian heritage buildings at risk due to differential ground movements. In the last decade, Persistent Scatterer SAR interferometry (PS-InSAR) has proven to be a powerful technique for analysing earth surface deformation. In order to identify the level of risk at national and local scales, this information is integrated with the Belgian heritage data by means of a GIS environment interactive toolbox and fusion modules. This paper presents a description of the methodology implemented in the project together with the case study of Saint-Vincent church, located in Zolder in a former colliery zone, for which damage is assessed.

Land Surface Temperature (LST) and Land Surface Emissivity (LSE) are common retrievals from thermal hyperspectral imaging. However, their retrieval is not a straightforward procedure because the mathematical problem is ill-posed. This procedure becomes more challenging in an urban area where the spatial distribution of temperature varies substantially in space and time. In this study we propose a new method which integrates 3D surface information from LIDAR data in an attempt to improve the temperature and emissivity separation (TES) procedure for thermal hyperspectral scene. The experimental results prove the high accuracy of the proposed method in comparison to another conventional TES model.

The forecast of human population distribution in Africa is limited by the lack of spatial urban expansion model and the quality of its data sources. One way to overcome this shortcoming is to integrate multi-source and multi-temporal data for improving the delineation and the characterization of human settlements. This paper presents a fully automatic fusion processing scheme of multi-temporal SAR and optical data for improving the segmentation of African urban areas.

This paper presents a new algorithm for the analysis of linear spectral mixtures in the thermal infrared domain, with the goal to jointly estimate the abundance and the subpixel temperature in a mixed pixel, i.e., to estimate the relative proportion and the temperature of each material composing the mixed pixel. This novel approach is a two-step procedure. First, it estimates the emissivity and the temperature over pure pixels using the standard temperature and emissivity separation (TES) algorithm. Second, it estimates the abundance and the subpixel temperature using a new unmixing physics-based model, called Thermal Remote sensing Unmixing for Subpixel Temperature (TRUST). This model is based on an estimator of the subpixel temperature obtained by linearizing the black body law around the mean temperature of each material. The abundance is then retrieved by minimizing the reconstruction error with the estimation of the subpixel temperatures. The TRUST method is benchmarked on simulated scenes against the fully constrained least squares unmixing applied on the radiance and on the estimation of surface emissivity using the TES algorithm. The TRUST method shows better results on pure and mixed pixels composed of two materials. TRUST also shows promising results when applied on thermal hyperspectral data acquired with the Thermal Airborne Spectrographic Imager during the Detection in Urban scenario using Combined Airborne imaging Sensors campaign and estimates coherent localization of mixed-pixel areas.

The estimation of surface emissivity and temperature from thermal hyperspectral data is a challenge. Methods that estimate the temperature and emissivity on a pixel composed by one single material exist. However, the estimation of the temperature on a mixed pixel, i.e. a pixel composed by more than one material, is more complex and has scarcely been investigated in the literature. This paper addresses this issue by proposing an estimator which linearizes the Black Body law around the mean temperature of each material. The performance of this estimator is studied using simulated data with different hyperspectral sensor configurations and under various noise conditions. The obtained results are encouraging and show an accuracy on the estimated temperature of 0.5 K while using high spectral resolution sensor.

The estimation of surface emissivity and temperature from thermal hyperspectral data is a challenge. There are several methods that estimate the temperature and the emissivity by assuming that the pixel is composed by a single material. However, the estimation of the temperature on a mixed pixel, i.e. a pixel composed by more than one material, is more complex and has scarcely been investigated in the literature. This paper addresses this issue by jointly estimating the materials composing the mixed pixel and their temperatures. It uses an unmixing method based on the linearization of the Black Body law. The performance of this strategy is studied using synthetic data and a real thermal image acquired by the TASI sensor.

Thermal hyperspectral imaging (THI) extends the activities of automatic spectral based target detection to the thermal infrared spectral range. This imaging technique which allows the detection of targets regardless of illumination, unfortunately, frequently suffers from high false alarm rates due to the high noise contained in the image. This study develops a new Normalised Difference Thermal Index NDTIMMwhich allows the physics -based segmentation of Man-Made objects in the scene. This index produces quick and efficient separation of man-made objects containing silicate minerals from other natural and man-made materials. The change detectors are spatially adapted to segments which present different NDTIMMratios. As a result, the scene is enhanced and the performances of change detection methods which are based on NDTIMMsegments distance are significantly improved.

The results present in this paper, show the improvement of 15%-17% in the accuracy for most of the classes while applying SEM-S method.

In an effort to overcome the limitations of small target detection in complex urban scene, complementary data sets are combined to provide additional insight about a particular scene. This paper presents a method based on shape/spectral integration (SSI) decision level fusion algorithm to improve the detection of vehicles in semi and deep shadow areas. A four steps process combines high resolution LIDAR and hyperspectral data to classify shadow areas, segment vehicles in LIDAR data, detect spectral anomalies and improves vehicle detection. The SSI decision level fusion algorithm was shown to outperform detection using a single data set and the utility of shape information was shown to be a way to enhance spectral target detection in complex urban scenes.

In this paper, a shadow detection method combining hyperspectral and LIDAR data analysis is presented. First, a rough shadow image is computed through line-of-sight analysis on a Digital Surface Model (DSM), using an estimate of the position of the sun at the time of image acquisition. Then, large shadow and non-shadow areas in that image are detected and used for training a supervised classifier (a Support Vector Machine, SVM) that classifies every pixel in the hyperspectral image as shadow or non- shadow. Finally, small holes are filled through image morphological analysis. The method was tested on data including a 24 band hyperspectral image in the VIS/NIR domain (50 cm spatial resolution) and a DSM of 25 cm resolution. The results were in good accordance with visual interpretation. As the line-of-sight analysis step is only used for training, geometric mismatches (about 2 m) between LIDAR and hyperspectral data did not affect the results significantly, nor did uncertainties regarding the position of the sun.

Hyperspectral change detection has been proved to be a promising technique for detecting indiscernible targets in different background. However, in the case of dense industrial and urban areas the complexity of the terrain and the multi-temporal images, which include positional deviation, radiant and atmospheric variation, shadows and spatial structure alteration, severely affects the automation of the change detection. This paper develops and enlarges four clustering based methods to detect man-made changes in VNIR and TIR hyperspectral scenes. The first applied method is Covariance-Equalisation (CE) multivariate statistical techniques, which detects differences between linear combinations of the spectral bands from the two acquisitions. The other three methods perform clustering of a reference image and then detect changes in a target image using a class-conditional distance detector: (a) class-conditional CE (QCE), (b) bi-temporal QCE and (c) Wavelength Dependent Segmentation (WDS). For the detection of small changes in industrial and urban areas, data from two flight campaigns were used: AHS-160 over the port of Antwerp and over the city of Kalmthout (Belgium). It was found that the use of a spatially adaptive detector greatly increases change-detection performance for both target detection and false alarm reduction. Moreover, WDS clustering based methods demonstrated a substantial improvement in change detection when applied on combined-wavelengths (as MWIR and LWIR or VNIR and TIR) hyperspectral data sets with respect to a single-wavelength data set.