This study conducts the first regional mapping exercise of landscape dynamics of the Kerguelen Archipelago; a remote sub-Antarctic archipelago located in the southern Indian Ocean. It is based on an original adaptation of the radiometric landscape methodology applied to the long time series of MODIS NDVI data covering the period 2003-2022, allowing the temporal dimension to be explicitly integrated into the regional-scale landscape mapping. The aim is to provide a comprehensive framework for analyzing the structure, dynamics, and evolutionary trajectories of the landscapes of this sub-Antarctic archipelago, which remain largely unknown yet essential for understanding ecosystem functioning in isolated environments. The adopted approach is based on three complementary steps. First, synthetic variables were extracted from the NASA's MODIS NDVI product to summarize seasonal and interannual information. Next, spatial segmentation was used to group pixels into radiometrically homogeneous objects, constituting basic units of the landscape. Finally, unsupervised clustering was applied to classify these units and produce a coherent landscape typology. This original data-driven approach overcomes the limitations of supervised classifications based on predefined criteria by distinguishing landscapes that may appear similar at a given moment but have divergent NDVI value trajectories over two decades. The analysis led to the identification of five major landscape units, revealing different dynamics at the regional scale. The integration of outputs from the MAR regional climate model and the NASADEM digital elevation model made it possible to place these landscape units in their environmental and topographical context. The results show that landscape stratification follows a marked altitudinal gradient, which strongly influences the distribution and evolution of radiometric landscape units. Beyond producing unprecedented mapping, this approach constitutes the first regional, remote sensing data-driven geographical partitioning of a sub-Antarctic archipelago based on long-term vegetation trajectories. It provides a foundational environmental framework that can serve as a baseline for future field-based investigations, comparative analyses between/within the five identified landscape units, and multi-scale ecological studies focusing on specific environments. By capturing the specific values and evolutionary trajectories of vegetation, this methodology makes it possible to establishes an initial typology of the archipelago's landscapes, while providing insights to better understand the interactions between climate, relief, and vegetation. Our approach contributes to improving the knowledge and monitoring of landscapes in remote sub-Antarctic environments. As a territory managed by the Terres Australes et Antarctiques Fran & ccedil;aises (TAAF), the Kerguelen Archipelago constitutes a sentinel of environmental change in the Southern Hemisphere. The proposed methodology provides regional and national decision-makers with a robust tool for long-term ecosystem and landscape monitoring, supporting management and conservation strategies adapted to these particularly fragile environments that are highly vulnerable to climate change.

Remote sensing science is expected to produce spatio-temporal indicators to help societies to address major global challenges. In this regard, we have implemented the CHOVE-CHUVA web platform to monitor socio-environmental dynamics in the Brazilian Amazon state of Mato Grosso. Result of a long-term collaboration between research labs, local NGOs, and administrations, this Space for Climate Observatory initiative relies on two major pillars: (1) visualizing and computing spatio-temporal indices derived from Earth Observation data and (2) collecting citizen information as part of collaborative science. A major asset of the platform is to gather, visualize, and process data covering a wide range of themes such as land status, land use, climate, natural vegetation, agriculture, and hydrology. The collaborative information refers to land use types that are still unusual in Mato Grosso, i.e., forest restoration and low-carbon agricultural practices. The implementation of the platform was based on a French open source geospatial data infrastructure named PRODIGE. Prospects for enhancing the platform include integrating new thematic information, making better use of raw Earth Observation data, improving interactions with end-users to better capture their interpretation of socio-environmental dynamics, and improving the platform’s efficiency to update data and process large study areas.

Les paysages agricoles du Nord et Centre Bénin connaissent une forte mutation. L’essor du coton, du soja et de l’anacarde, associé à la croissance démographique et à la mécanisation, provoquent l’abandon des jachères, la dégradation des sols, la réduction du couvert arboré et la fragmentation des espaces pastoraux, générant des conflits fonciers et des tensions entre agriculteurs et éleveurs. Face à ces enjeux, les nouvelles données satellitaires offrent des perspectives prometteuses pour le suivi des dynamiques territoriales, mais cet usage reste limité en Afrique de l’Ouest. Dans ce contexte, le projet OBSYDYA vise à mettre en place un observatoire pilote produisant un service informationnel géospatial basé sur des indicateurs spatialisés issus de cartes d’occupation des sols produites annuellement à partir d’imagerie satellitaire et de données de terrain. Cet article présente et illustre l’étape de co-construction des indicateurs réalisée à travers des ateliers participatifs avec des acteurs locaux et l’analyse de la littérature scientifique. Au total, 21 indicateurs ont été identifiés dans deux domaines : 8 concernent l’agriculture (productions agricoles et intensification) et 13 concernent le pastoralisme (superficie et fragmentation des aires de parcours, accessibilité des couloirs de passage, distance aux points d’eau, sécurité des éleveurs). Pour illustrer la pertinence de ces indicateurs, un exemple est présenté pour chaque domaine sur six sites d’étude. Les résultats mettent en évidence une typologie marquée des villages en termes de productions et de pratiques d’intensification agricole, et la forte variation des conditions pastorales locales et saisonnières de ces mêmes territoires sous divers degrés d’intensification agricole. Ce travail démontre qu’en s’appuyant sur des cartes d’occupation des sols adaptées (nomenclature, précision, actualisation annuelle), les indicateurs agricoles et pastoraux constituent un outil robuste pour analyser les structures et dynamiques paysagères et ainsi appuyer les politiques agricoles et territoriales en Afrique de l’Ouest.

The agricultural landscapes of North and Centre Benin are undergoing rapid transformation. The expansion of cotton, soy, and cashew production - coupled with population growth and mechanization - has led to the abandonment of fallow periods, soil degradation, reduced tree cover, and fragmented pastoral areas. These changes have intensified land-use conflicts and tensions between farmers and herders. In response, satellite data offer promising opportunities for monitoring territorial dynamics, but their use remains limited in West Africa. In this context, the OBSYDYA project aims to establish a pilot observatory that provides a geospatial information service based on spatially explicit indicators derived from annual land cover maps produced using satellite imagery and field data. This paper presents and illustrates the co-construction of these indicators through participatory workshops with local stakeholders and a review of the scientific literature. A total of 21 indicators were identified across two domains: 8 related to agriculture (agricultural productions and intensification) and 13 related to pastoralism (grazing area size and fragmentation, accessibility of migration corridors, distance to water points, herder safety). To illustrate the relevance of these indicators, an example is provided for each domain across six study sites. The results reveal a distinct typology of sites in terms of agricultural productions and intensification, as well as significant local and seasonal variation in pastoral conditions under different levels of agricultural intensification. This work demonstrates that, by relying on tailored land cover maps with appropriate nomenclature, precision, and annual updates, agricultural and pastoral indicators can serve as robust tools for analyzing landscape structures and dynamics, thereby supporting agricultural and territorial policies in West Africa.

The Brazilian Amazon state of Mato Grosso has undergone rapid agricultural expansion and intensification in recent decades, leading to land depletion and high carbon emissions. Since 2010, the low-carbon agricultural Plan (ABC Plan) promotes practices to limit greenhouse gas emissions while increasing productivity. Among these practices, the adoption of intra-annual integrated crop-livestock systems (ICLS) is encouraged and can be monitored by remote sensing, especially through dense satellite image time series (SITS) and advanced analysis tools. In this study, we compare a calibrated Random Forest and three deep learning methods (LSTM, LTAE and TempCNN) suitable for processing SITS for mapping intra-annual ICLS in Mato Grosso. In particular, MODIS time series were used to classify a spatially and temporally rich dataset among four classes (pasture, single-crop, double-crop and intra-annual ICLS). TempCNN achieved slightly higher overall results in terms of precision (85.63%), recall (85.71%) and F1-score (85.32%), even though there is an inter-class and intraclass heterogeneity in the results. For the ICLS class, TempCNN achieved the best precision (85.14%) but Random Forest achieved higher recall (69.63% vs. 58.52% for TempCNN) and F1-Score (70.14% vs. 69.36% for TempCNN).

Deforestation, degradation and regrowth of the tropical forests of the Amazon clearly alter forest cover. These changes in space and over time generate diverse landscape use (archetypes). Identifying the differences and similarities between units and associated changes in forest cover due to deforestation, degradation and regrowth is crucial for context-specific management and planning. Methods for quantitatively characterizing this complexity across large agricultural frontiers are still underdeveloped. This article presents a new method to study the archetypes resulting from forest cover changes in Amazonian subnational jurisdictions by integrating spatial and temporal analysis techniques for deforestation, degradation and regrowth. The weighted k-means approach was linked to nine metrics covering the period 1990-2021 in three subnational jurisdictions of the Brazilian and Colombian Amazon: 1. baseline forest, 2. percentage forest loss, 3. remaining forest, 4. speed of forest loss, 5. active deforestation, 6. percentage forest degradation, 7. speed of forest degradation, 8. active degradation, and 9. percentage regrowth. Four optimal archetypes were chosen using k-means classification: a. consolidated frontier, b. vulnerable frontier, c. past gradual frontier and d. rampant frontier. Consolidated frontiers are areas with high and long term deforestation. Vulnerable frontiers have high forest cover but show signs of previous or recent deforestation and degradation. Past gradual and rampant frontiers show medium to high levels of deforestation associated with degradation. The importance and spatial distribution of each archetype varies at a territorial scale depending on colonization history and on the drivers of deforestation and degradation. This approach provides valuable insights for stakeholder to target interventions and policies adapted to each archetype, for example, payment for ecosystem services, command and control policies, land tenure regulations, land restoration strategies or land use intensification.

Landscape mapping has the potential to address some of the most pressing research issues of our time, including climate change, sustainable development, and human well-being. In this paper, we propose an original method that lays the foundations for landscape mapping and overcomes some of the major limitations of existing biophysical methods. Based on the assumption that the primary components of the landscape can be extracted directly from the radiometric information of satellite image time series, this paper presents a new approach to landscape characterization and mapping based solely on remote sensing data. The approach relies on a conceptual model, which links the description, characteristics, structure and functions of the landscape to a set of Remote Sensing-based Essential Landscape Variables (RS-ELVs). The RS-ELVs are then processed according to geographic object-based image analysis (GEOBIA) approach to produce a radiometric landscape map. The model and the remote sensing data processing chain are tested on a case study in central Madagascar (about 13 000 km2) composed of contrasting landscapes resulting from different climatic conditions and agricultural practices. The RS-ELVs are extracted from MODIS image time series for the temporal and spectral variables, and from MODIS and Sentinel-2 images for the texture variables. The parameterization of the segmentation and clustering algorithms is determined by statistical optimization. The final result is a radiometric landscape map in six classes. The landscape classes are then characterized using an independent set of remote sensing variables, a global land cover map and ground observations. The approach successfully identifies and delineates the gradient and major landscape types of the complex region of central Madagascar, confirming our initial hypothesis. The production of such radiometric landscape maps opens the way for integrated territorial development, including the planning and protection of the living environment and human well-being, and the implementation of sectoral policies.

The CHOVE-CHUVA project is a Space for Climate Observatory initiative aiming at developing operational tools to monitor socio-environmental dynamics in the Brazilian state of Mato Grosso, in the Southern Amazon. This project focuses on the dissemination of remote sensing-based spatial information to monitor the evolution of climate variables and land use dynamics, especially regarding agriculture, natural vegetation and hydrological resources. The platform is enhanced by the collection of collaborative data about the adoption of specific land use types (e.g. forest restoration and crop-livestock-forest integrated systems) encouraged by the Brazilian program for a low-carbon agriculture (ABC plan).

As global land cover/ land use change (LULCC) threatens the human's well-being, accurate detection and characterization of LULCC is of paramount importance. The increasing availability of dense satellite image time series (SITS), together with the ever-improving change detection algorithms, has allowed significant progress to be made. However, much remains to be done in its characterization. This study aims to uncover potential relationships between changes in Normalized Difference Vegetation Index (NDVI) SITS patterns and their drivers. It distinguishes itself by representing phenological changes not only as transitions between specific patterns, but also by examining the nature of these changes-whether abrupt, gradual, or seasonal. For seasonal changes, it further refines the analysis to determine their impact on the amplitude, number of seasons (NOS), or length of seasons (LOS) components. Our focus is to provide insights into the land dynamics and drivers of change in Senegal using an RGB (red, green, blue) composite change map. This map is derived from three MODIS NDVI time series change metrics detected by BFASTm-L2 within the MODIS NDVI 2000-2021 SITS: magnitude of change, direction of change, and dissimilarity of time series shape. The 250-meter resolution MODIS data served as an optimal data source for this analysis due to its high temporal resolution (near daily) and extensive coverage over 20 years. The sensitivity of each metric to different types of change was first tested on a simulated dataset before being applied to the MODIS SITS. The RGB change map enabled visualization of different "signatures" of change, which, combined with ground information, rainfall data, NDVI time series analysis, and Google Earth imagery, helped link these signatures to various drivers of change. Climatic and anthropogenic changes, such as those induced by Large Scale Agricultural Investments (LSAI) or mining, were visually inferred from the RGB map.This approach demonstrates the usefulness of integrating the type of change, especially seasonal change, into the characterization of land change. This method has the advantage of being fast, interpretable, robust to noise and easily transferable to different regions.

In the context of Global Change Research, detection, monitoring and characterization of land use/land cover (LULC) changes are of prime importance. The increasing availability of dense satellite image time series (SITS) has led to a shift in the change detection paradigm, with algorithms able to exploit the full temporal information laid down in SITS. So far, most of these algorithms have focused on the detection of abrupt and gradual changes, and thus developed breakpoint detection based on significant deviations from the mean. However, LULC changes may manifest themselves in other patterns, particularly changes in seasonality (amplitude, number and length of the growing seasons) that are harder to detect. In this paper, we propose a simple method to automatically select the breakpoint linked to the biggest seasonal change in long and dense SITS with multiple breakpoints. This approach - BFASTm-L2 - relies on linking a high-speed algorithm (BFAST monitor) with a time series similarity metric (Euclidian distance L2) sensitive to seasonal changes. The capacity of BFASTm-L2 to identify the date of change in different situations was tested on two data sets, and compared to the performances of three other algorithms (BFAST monitor, BFAST lite, and Edyn). The data sets are 1. a published benchmark data set composed of 25 200 simulated SITS with different change types and change magnitudes, and 2. the 2000-2020 MODIS NDVI SITS over a 200x200 pixels area in Senegal including different study sites which have undergone recent LULC changes due to agricultural large-scale land acquisitions (LSLAs) (as reported in the ground field database used in this study). The results show that BFASTm-L2 is efficient in accurately detecting in time most of the changes, and, in contrast with BFAST Lite and BFASTmonitor, to spatially highlight LSLAs-induced changes without the need of any prior knowledge. The automatic proposed approach, faster than BFAST Lite and Edyn, and with very few tuneable parameters, may thus be easily implemented in unsupervised pipelines to map and analyse generic LULC changes at regional scale.

Non-active agricultural land (NAAL) mapping in West Africa is essential to accurately assess agricultural systems and its contribution to food security and agro-ecological sustainability of current practices, and yet the available mapping methodologies are not adapted to the environmental and cropping conditions encountered when addressing tropical smallholder agriculture. In this study we present a strategy that makes use of Sentinel-2 image time series, CHIRPS monthly rainfall data and multiple years of in-situ data obtained from the JECAM database to map NAAL in a Soudanian site in Burkina Faso (Koumbia) between the years 2016 and 2021. In a first step we generated annual land use maps in four broad classes (managed, unmanaged, evergreen and non-vegetated) to detect fields being actively cultivated in a given year, and in a second step, we used these annual land use maps to differentiate non-active agricultural land by identifying shifts from one year to another. For the validation part, we analyzed the sensitivity of classification accuracy to in-situ data pre-processing by building 5 experimental validation data sets. The unmanaged classes F1-scores of the land use maps ranged between 0.86 and 0.98, depending on the year, whereas NAAL classes F1-scores ranged from 0.75 to 0.92 when validated against the most restrictive data set (pixels with no missing reference data for the period considered). NAAL represents between 7% to 14% of the study site cropland depending on the year. The higher class probabilities are in areas where data was available, whereas the low probabilities are localized and linked to transition areas on the outskirts of the department. Our results indicate that a multi-annual approach can allow NAAL mapping under challenging environments, yet efforts are to be made to develop more cost-efficient unsupervised solutions.

The GEOGLAM crop monitor for early warning is based on the integration of the crop conditions assessments produced by regional systems. Discrepancies between these assessments can occur and are generally attributed to the interpretation of the vegetation and climate data. The premise of this article is that other sources of discrepancy related to the data themselves must also be considered. We conducted a comparative experiment of the growth vegetation anomalies routinely produced by four operational crop monitoring systems in West Africa [FEWSNET, GIEWS, ASAP, VAM] for the 2010–2020 period. We collected a set of normalized differences vegetation index-based indicators (% mean, % median, and Z-score) and proposed original methods to analyze and compare the spatio-temporal variations of these indices using Hovmöller representation, statistics, and spatial analysis. To facilitate systems comparison, a classification scheme based on the percentile rank values of anomaly indicators was applied to produce 3-class alarm maps (negative, absence, and positive anomalies). Results show that, on an annual basis, the per-pixel similarity is relatively low between the four systems [24.5%–34.1%], and that VAM and ASAP are the most similar (70%). The reasons of the products discrepancies come mainly from different preprocessing methods, especially the choice of the reference period used to calculate the anomaly. The negative alarm agreement classes show no eco-climatic zoning influence, but negative alarms hot-spots were locally observed. The negative alarm agreement maps can be a useful tool for early warning as they synthesize the information provided by the different systems, with a confidence level.

Food Security (FS) is a major concern in West Africa, particularly in Burkina Faso, which has been the epicenter of a humanitarian crisis since the beginning of this century. Early warning systems for FS and famines rely mainly on numerical data for their analyses, whereas textual data, which are more complex to process, are rarely used. However, this data is easy to access and represents a source of relevant information that is complementary to commonly used data sources. This study explores methods for obtaining the explanatory context associated with FS from textual data. Based on a corpus of local newspaper articles, we analyze FS over the last ten years in Burkina Faso. We propose an original and dedicated pipeline that combines different textual analysis approaches to obtain an explanatory model evaluated on real-world and large-scale data. The results of our analyses have proven how our approach provides significant results that offer distinct and complementary qualitative information on food security and its spatial and temporal characteristics.

Background The timely and accurate identification of food insecurity situations represents a challenging issue. Household surveys are routinely used in low-income countries and are an essential tool for obtaining key food security indicators that are used by decision makers to determine the targets of food security interventions. Methodology This paper investigates the spatial and temporal quality of the food security indicators obtained through household surveys. The empirical case of Burkina Faso is used in this paper, where a large-scale rural household survey has been conducted yearly since 2009. From this data set, three food security indicators (the Food Consumption Score, the Household Dietary Diversity Score and the Coping Strategies Index) are calculated at the regional level for each year during the 2009–2017 period. Results Results highlight that observed spatiotemporal variations in these indicators are consistent with the major regional food shocks reported in food warning system reports and are significantly correlated with variations computed from other sources of data, such as satellite images, rainfall and food prices. Conclusion These results raise new research questions on food security monitoring systems and on the use of heterogeneous data and multiple food security indicators.

The phenology of tropical forests is tightly related to climate conditions. In the Amazon, the seasonal greening of forests is conditioned by solar radiation and rainfall. Yet, increasing anthropogenic pressures (e.g. logging and wildfires), raise concerns about the impacts of forest degradation on the functioning of forest ecosystems, especially in a climate change context. In this study, we relied on remote sensing data to assess the contribution of solar radiation and precipitation to forest greening in mature and fire degraded forests, with a focus on the 2015 drought event. Our results showed that forest greening is more dependent on water resources in degraded forests than in mature forests. As a consequence, the expected increase in drought episodes and associated fire occurrences under climate change could lead to a long-term drying of tropical forests.

Due to different combinations of agriculture, livestock and forestry managed by rotation, succession and intercropping practices, integrated agriculture production systems such as integrated crop–livestock systems (iCL) constitute a very complex target and a challenge for automatic mapping of cropping practices based on remote sensing data. The overall objective of this study was to develop a classification strategy for the annual mapping of integrated Crop–Livestock systems (iCL) at a regional scale. This strategy was designed and tested in the six agro-climatic regions of Mato Grosso, the largest Brazilian soybean producer state, using MODIS satellite time-series images acquired between 2012 and 2019, ground data with heterogeneous distribution in space and time and a Random Forest classifier. The results showed that: 1. the use of unbalanced training samples with a class composition close to the real one was the right classifier training strategy; 2. the use of a single training database (pooling samples from different years and regions) to classify each region and year individually proved to be robust enough to provide similar classification accuracies in comparison to those based on the use of a database acquired for each region and for each year. The final hierarchical classification overall accuracy was 0.89 for Level 1, the cropping pattern level (single and double crops DC); 0.84 for Level 2, the DC category level (integrated system iCL soy-pasture/brachiaria, soy-cotton and soy-cereal); 0.77 for Level 3, the iCL level (iCL1 soy-pasture and iCL2 soy-pasture mixed with corn). The F-scores for DC, iCL and iCL1 cropping systems presented high accuracy (0.89, 0.85 and 0.84), while iCL2 was more difficult to classify (0.63). This approach will next be applied across the entire Brazilian soybean corridor, leading to an operational tool for monitoring the adoption of sustainable intensification practices recognized by Brazil’s Agriculture Low Carbon Plan (ABC PLAN).

Around the world, SDMs have been widely used to support forest management planning and biodiversity conservation. Beyond the prediction of species distribution provided by the SDMs, this study aimed to analyze the spatial distribution of tree species diversity using SDMs. The study area is a Faidherbia albida parkland in Central Senegal. It is characterized by a tree-based farming system dominated by Faidherbia albida.Using a robust and representative dataset of 9258 tree species occurrence, we first determined by an SDM the current potential spatial distribution of the 16 main tree species forming the parkland. Specifically, using 6 SDM algorithms and applying several modeling techniques with different categories of predictor variables (e.g., climate, topography, soil properties and human impact) we benchmarked 576 SDMs to achieve best model predictions for tree species. Then, tree species diversity maps were created on the basis of the resulting SDM predictions. Finally, the spatial dynamics of tree species diversity were discussed in relation to landscape characteristics, including heterogeneity, composition and human impact.The results showed that there is no single ‘best’ SDM algorithm (among the 6 algorithms tested) or modeling approach for all species. Benchmarking several modeling techniques allowed strengthening SDM performance, achieving AUC values that ranged from 0.64 (intermediate accuracy) to 0.87 (very good accuracy). The spatial dynamics of tree species diversity is related to the landscape heterogeneity and composition. In the Sahelian agroforestry systems (AFS), tree diversity is sustained by anthropization. A significant negative correlation with the distance to the village was found, i.e. the closer you get to the village, the greater the diversity of trees.This study could be crucial for analyzing tree species diversity when abundance information is not available.

After many years of decline, hunger in Africa is growing again. This represents a global societal issue that all disciplines concerned with data analysis are facing. The rapid and accurate identification of food insecurity situations is a complex challenge. Although a number of food security alert and monitoring systems exist in food insecure countries, the data and methodologies they are based on do not allow for comprehending food security in all its complexity. In this study, we focus on two key food security indicators: the food consumption score (FCS) and the household dietary diversity score (HDDS). Based on the observation that producing such indicators is expensive in terms of time and resources, we propose the FSPHD (Food Security Prediction based on Heterogeneous Data) framework, based on state-of-the-art machine and deep learning models, to enable the estimation of FCS and HDDS starting from publicly available heterogeneous data. We take into account the indicators estimated using data from the Permanent Agricultural Survey conducted by the Burkina Faso government from 2009 to 2018 as reference data. We produce our estimations starting from heterogeneous data that include rasters (e.g., population density, land use, soil quality), GPS points (hospitals, schools, violent events), line vectors (waterways), quantitative variables (maize prices, World Bank variables, meteorological data) and time series (Smoothed Brightness Temperature — SMT, rainfall estimates, maize prices). The experimental results show a promising performance of our framework, which outperforms competing methods, thus paving the way for the development of advanced food security prediction systems based on state-of-the-art data science technologies.

Food security is a major concern in West Africa, particularly in Burkina Faso, which has been the epicenter of a humanitarian crisis since the beginning of this century. Early warning systems for food insecurity and famines rely mainly on numerical data for their analyses, whereas textual data, which are more complex to process, are rarely used. To this end, we propose an original and dedicated pipeline that combines different textual analysis approaches (e.g., word embedding, sentiment analysis, and discrimination calculation) to obtain an explanatory model evaluated on real-world and large-scale data. The results of our analyses have proven how our approach provides significant results that offer distinct and complementary qualitative information on the food security theme and its spatial and temporal characteristics.