Ms. Joyce Mongai Chindong is an emerging researcher in geospatial sciences whose work centers on leveraging GIS, remote sensing, and machine learning to improve environmental monitoring in data-scarce regions. Her research primarily focuses on soil degradation processes, including drought dynamics and soil salinity, by integrating multi-sensor satellite observations, proximal sensing techniques, and advanced analytical frameworks. She applies Earth Observation data—such as remotely sensed precipitation products, vegetation indices like NDVI, and field-based spectral and electrical conductivity measurements—to quantify environmental anomalies and assess ecosystem responses to climatic variability. Ms. Chindong’s work emphasizes methodological rigor through preprocessing workflows, anomaly detection, spatial modeling, and the use of supervised learning algorithms to generate accurate, scalable predictions of land surface conditions. Her recent contribution, a multi-sensor machine learning framework for field-scale soil salinity mapping, demonstrates her commitment to developing robust, transferrable solutions for sustainable land management, particularly in resource-limited environments where environmental data is sparse. By combining optical, radar, and ground-based measurements with algorithmic modeling, she advances the precision and reliability of landscape-level assessments that support agricultural resilience and environmental planning. Motivated by global sustainability goals, Ms. Chindong aims to refine geospatial intelligence to better understand environmental processes across diverse landscapes. Her interdisciplinary approach—blending geoinformation science, environmental monitoring, and computational methods—positions her as a promising contributor to research on land degradation, climate impacts, and data-driven environmental decision-making.
Profile: Orcid
Featured Publication
Chindong, J. M., Ouzemou, J.-E., Laamrani, A., El Battay, A., Hajaj, S., Rhinane, H., & Chehbouni, A. (2025). A multi-sensor machine learning framework for field-scale soil salinity mapping under data-scarce conditions. Remote Sensing, 17(22), Article 3778.