Accurate and efficient crop maps are essential for decision-makers to improve agricultural monitoring and management, thereby ensuring food security. The integration of advanced artificial intelligence (AI) models with hyperspectral remote sensing data, which provide richer spectral information than multispectral imaging, has proven highly effective in the precise discrimination of crop types. This systematic review examines the evolution of hyperspectral platforms, from Unmanned Aerial Vehicle (UAV)-mounted sensors to space-borne satellites (e.g., EnMAP, PRISMA), and explores recent scientific advances in AI methodologies for crop mapping. A review protocol was applied to identify 47 studies from databases of peer-reviewed scientific publications, focusing on hyperspectral sensors, input features, and classification architectures. The analysis highlights the significant contributions of Deep Learning (DL) models, particularly Vision Transformers (ViTs) and hybrid architectures, in improving classification accuracy. However, the review also identifies critical gaps, including the under-utilization of hyperspectral space-borne imaging, the limited integration of multi-sensor data, and the need for advanced modeling approaches such as Graph Neural Networks (GNNs)-based methods and geospatial foundation models (GFMs) for large-scale crop type mapping. Furthermore, the findings highlight the importance of developing scalable, interpretable, and transparent models to maximize the potential of hyperspectral imaging (HSI), particularly in underrepresented regions such as Africa, where research remains limited. This review provides valuable insights to guide future researchers in adopting HSI and advanced AI models for reliable large-scale crop mapping, contributing to sustainable agriculture and global food security.

Africa’s rapidly growing population is driving unprecedented demands on agricultural production systems. However, agricultural yields in Africa are far below their potential. One of the challenges leading to low productivity is Africa‘s poor soil quality. Effective soil fertility management is an essential key factor for optimizing agricultural productivity while ensuring environmental sustainability. Key soil fertility properties—such as soil organic carbon (SOC), nutrient levels (i.e., nitrogen (N), phosphorus (P), potassium (K), moisture retention (MR) or moisture content (MC), and soil texture (clay, sand, and loam fractions)—are critical factors influencing crop yield. In this context, this study conducts an extensive literature review on the use of hyperspectral remote sensing technologies, with a particular focus on freely accessible hyperspectral remote sensing data (e.g., PRISMA, EnMAP), as well as an evaluation of advanced Artificial Intelligence (AI) models for analyzing and processing spectral data to map soil attributes. More specifically, the study examined progress in applying hyperspectral remote sensing technologies for monitoring and mapping soil properties in Africa over the last 15 years (2008–2024). Our results demonstrated that (i) only very few studies have explored high-resolution remote sensing sensors (i.e., hyperspectral satellite sensors) for soil property mapping in Africa; (ii) there is a considerable value in AI approaches for estimating and mapping soil attributes, with a strong recommendation to further explore the potential of deep learning techniques; (iii) despite advancements in AI-based methodologies and the availability of hyperspectral sensors, their combined application remains underexplored in the African context. To our knowledge, no studies have yet integrated these technologies for soil property mapping in Africa. This review also highlights the potential of adopting hyperspectral data (i.e., encompassing both imaging and spectroscopy) integrated with advanced AI models to enhance the accurate mapping of soil fertility properties in Africa, thereby constituting a base for addressing the question of yield gap.

This paper analyse and compare the difference between the reflectance in the homologous spectral bands of MSI and OLI sensors, VNIR and SWIR, for high temporal frequency monitoring of soil salinity dynamic in an arid landscapes. In addition, their conversion in term of Soil Salinity and Sodicity Index and in term of Semi-Empirical Predictive Model for soil salinity mapping were compared, and their sensor differences were quantified. To achieve these, analyses were performed on simulated data and on two pairs of images acquired over the same area in July 2015 and August 2017 with one day difference between each pair. For simulated data, a field survey was organized and 160 soil samples were collected with various degrees of soil salinity classes. The bidirectional reflectance factor was measured above each soil sample in a Goniometric-Laboratory using an ASD spectroradiometer. These measurements were resampled and convolved in the solar-reflective bands of SMI and OLI using the CAM5S RTC and the relative spectral response profiles characterizing the filters of these instruments. Furthermore, the used pairs of images were not cloudy, or cirrus contaminated, and without shadow effects. They were radiometrically and atmospherically corrected, and the differences related to BRDF were normalized. Therefore, obtained results show that we can conclude that the MSI and OLI sensors can be used jointly to characterize and to monitor accurately the soil salinity and it's dynamic in time and space in arid landscape, provided that rigorous preprocessing issues must be addressed before.

Accurate mapping of soil organic carbon (SOC) supports sustainable land management practices and carbon accounting initiatives for mitigating climate change impacts. This study presents a novel meta-learner framework that combines multiple machine learning algorithms and spectra processing algorithms to optimize SOC prediction using the PRISMA hyperspectral satellite imagery in the Doukkala plain of Morocco. The framework employs a two-layer structure of prediction models. The first layer consists of Random Forest (RF), Support Vector Regression (SVR), and Partial Least Squares Regression (PLSR). These base models were configured using data smoothing, transformation, and spectral feature selection techniques, based on a 70/30% data split. The second layer utilizes a ridge regression model as a meta-learner to integrate predictions from the base models. Results indicated that RF and SVR performance improved primarily with feature selection, while PLSR was most influenced by data smoothing. The meta-learner approach outperformed individual base models, achieving an average relative improvement of 48.8% over single models, with an R² of 0.65, an RMSE of 0.194%, and an RPIQ of 2.247. This study contributes to the development of methodologies for predicting and mapping soil properties using PRISMA hyperspectral data.

Soil salinity is a major constraint to soil health and crop productivity, especially in arid and semi-arid regions. The most accurate measurement of soil salinity is considered to be the electrical conductivity of saturated soil extracts (EC_e). Because this method is labor-intensive, it is unsuitable for routine analysis in large soil sampling campaigns. This study aimed to identify the best models to estimate soil salinity based on EC_e in relation to a rapid electrical conductivity (EC) measurement in soil/water (referred to as S:W henceforward) extracts. We evaluated the relationship between EC_e and the EC_S:W extract ratios (1:1, 1:2, and 1:5) in salt-affected soils from the semi-arid Sehb El Masjoune region of Morocco. The soil salinity in this region is 0.5 to 235 dS/m, as determined by the EC_e method. A total of 125 soil samples, from topsoil (0–15 cm) and subsoil (15–30 cm) with mainly fine to medium textures, were analyzed using linear, logarithmic, and second-order polynomial regression models. The models included all samples or grouped samples according to soil texture (fine, medium) or specific textural classes. The mean EC_e values were 2.6, 3.1, and 7.9 times greater than the EC of 1:1, 1:2, and 1:5 S:W extracts, respectively. Polynomial regression models had the best predictive accuracy, R² = 0.98, and the lowest root mean square error of 10.6 to 10.7 dS/m for the EC_S:W extract ratios of 1:5 and 1:2. The polynomial models could represent the non-linear relationships between EC_e and salinity indicators, especially in the 80–170 dS/m salinity range, where other models typically underestimate the salinity. These results confirm that advanced regression techniques are suitable for predicting soil salinity in a salt-affected semi-arid region. The site-specific models outperformed previously published models, because they consider the spatial variability and heterogeneity of the salinity in the study area explicitly. This confirms the importance of calibrating soil salinity models according to the local soil and environmental conditions. Consequently, we can undertake soil salinity assessments in hundreds of samples by using the simple, rapid EC_S:W extraction method as a direct indicator of EC and extrapolate to EC_e with a polynomial regression model. Our approach enables the widespread soil salinity assessments that are needed for land-use planning, irrigation management, and crop selection in salt-affected landscapes.

Soil salinity severely constrains agricultural productivity and soil health, particularly in arid and semi-arid regions. Conventional salinity assessment methods are labor-intensive, time-consuming, and spatially limited. This study developed a data-scarce workflow integrating proximal sensing (EM38-MK2), very high-resolution multispectral imagery, and machine learning to map soil salinity at field scale in the semi-arid Sehb El Masjoune area, central Morocco. A total of 26 soil samples were analyzed for Electrical Conductivity (EC), and 500 Apparent Electrical Conductivity (ECa) measurements were collected and calibrated using the field samples. Spectral and topographic covariates derived from Unmanned Aerial Vehicle (UAV) and PlanetScope imagery supported model training using Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), Random Forest (RF), and a Stacked Ensemble Learning Model (ELM). Regression Kriging (RK) was applied to model residuals to improve spatial prediction. ELM achieved the highest accuracy (R² = 0.87, RMSE ≈ 4.15), followed by RF, which effectively captured nonlinear spatial patterns. RK improved PLSR accuracy (by 11.1% for PlanetScope, 13.8% for UAV) but offered limited gains for RF, SVR, and ELM. SHAP analysis identified topographic covariates as the most influential predictors. Both UAV and PlanetScope delineated similar saline–sodic zones. The study demonstrates the following: (1) a scalable, data-efficient workflow for salinity mapping; (2) model and RK performance depend more on algorithmic design than sensor type; (3) interpretable ML and spatial modeling enhance understanding of salinity processes in semi-arid systems.