This work introduces a method that combines remote sensing and deep learning into a framework that is tailored for accurate, reliable and efficient counting and sizing of plants in aerial images. The investigated task focuses on two low-density crops, potato and lettuce. This double objective of counting and sizing is achieved through the detection and segmentation of individual plants by fine-tuning an existing deep learning architecture called Mask R-CNN. This paper includes a thorough discussion on the optimal parametrisation to adapt the Mask R-CNN architecture to this novel task. As we examine the correlation of the Mask R-CNN performance to the annotation volume and granularity (coarse or refined) of remotely sensed images of plants, we conclude that transfer learning can be effectively used to reduce the required amount of labelled data. Indeed, a previously trained Mask R-CNN on a low-density crop can improve performances after training on new crops. Once trained for a given crop, the Mask R-CNN solution is shown to outperform a manually-tuned computer vision algorithm. Model performances are assessed using intuitive metrics such as Mean Average Precision (mAP) from Intersection over Union (IoU) of the masks for individual plant segmentation and Multiple Object Tracking Accuracy (MOTA) for detection. The presented model reaches an mAP of $0.418$ for potato plants and $0.660$ for lettuces for the individual plant segmentation task. In detection, we obtain a MOTA of $0.781$ for potato plants and $0.918$ for lettuces.

Quantifying tree resources is essential for effectively implementing climate adaptation strategies and supporting local communities. In the Sahel, where tree presence is scattered, measuring carbon becomes challenging. We present an approach to estimating aboveground carbon (AGC) at the individual tree level using a combination of very high-resolution imagery, field-collected data, and machine learning algorithms. We populated an AGC database from in situ measurements using allometric equations and carbon conversion factors. We extracted satellite spectral information and tree crown area upon segmenting each tree crown. We then trained and validated an artificial neural network to predict AGC from these variables. The validation at the tree level resulted in an R ² of 0.66, a root mean square error (RMSE) of 373.85 kg, a relative RMSE of 78.6%, and an overestimation bias of 47 kg. When aggregating results at coarser spatial resolutions, the relative RMSE decreased for all areas, with the median value at the plot level being under 30% in all cases. Within our areas of study, we obtained a total of 3,900 Mg, with an average carbon content per tree of 330 kg. A benchmarking analysis against published carbon maps showed that 9 out of 10 underestimate AGC stocks, in comparison to our results, in the areas of study. An additional comparison against a method using only crown area to determine AGC showed an improved performance, including spectral signature. This study improves crown-based biomass estimations for areas where unmanned aerial vehicle or height data are not available and validates at the individual tree level using solely satellite imagery.

Food insecurity is a complex, multidimensional concept challenging to measure comprehensively. Effective anticipation, monitoring, and mitigation of food crises require timely and comprehensive global data. This paper introduces the Harmonized Food Insecurity Dataset (HFID), an open-source resource consolidating four key data sources: the Integrated Food Security Phase Classification (IPC)/Cadre Harmonisé (CH) phases, the Famine Early Warning Systems Network (FEWS NET) IPC-compatible phases, and the World Food Program’s (WFP) Food Consumption Score (FCS) and reduced Coping Strategy Index (rCSI). Updated monthly and using a common reference system for administrative units, the HFID provides comprehensive spatial and temporal coverage to the extent permitted by the available data. It serves as a vital tool for food insecurity experts and humanitarian agencies, providing a unified resource for analyzing food insecurity conditions and highlighting global data disparities and gaps. The scientific community can also leverage the HFID to develop data-driven predictive models, enhancing the capacity to forecast and prevent future food crises.

Surface water availability is a fundamental environmental variable to implement effective climate adaptation and mitigation plans, as expressed by scientific, financial and political stakeholders. Recently published requirements urge the need for homogenised access to long historical records at a global scale, together with the standardised characterisation of the accuracy of observations. While satellite altimeters offer world coverage measurements, existing initiatives and online platforms provide derived water level data. However, these are sparse, particularly in complex topographies. This study introduces a new methodology in two steps (1) teroVIR, a virtual station extractor for a more comprehensive global and automatic monitoring of water bodies, and (2) teroWAT, a multi-mission, interoperable water level processor, for handling all terrain types. L2 and L1 altimetry products are used, with state-of-the-art retracker algorithms in the methodology. The work presents a benchmark between teroVIR and current platforms in West Africa, Kazakhastan and the Arctic: teroVIR shows an unprecedented increase from $55\%$ to $99\%$ in spatial coverage. A large-scale validation of teroWAT results in an average of unbiased root mean square error ubRMSE of $0.638$ m on average for 36 locations in West Africa. Traditional metrics (ubRMSE, median, absolute deviation, Pearson coefficient) disclose significantly better values for teroWAT when compared with existing platforms, of the order of 8 cm and $5\%$ improved respectively in error and correlation. teroWAT shows unprecedented excellent results in the Arctic, using an L1 products-based algorithm instead of L2, reducing the error by almost 4 m on average. To further compare teroWAT with existing methods, a new scoring option, teroSCO, is presented, measuring the quality of the validation of time series transversally and objectively across different strategies. Finally, teroVIR and teroWAT are implemented as platform-agnostic modules and used by flood forecasting and river discharge methods as relevant examples. A review of various applications for miscellaneous end-users is given, tackling the educational challenge raised by the community.