This study was conducted in the Doukkala plain (western of Morocco), which has a semi-arid climate , to assess SOM levels and provide scenarios for remediating SOM depletion by rationally adding an organic amendment (manure or compost). Therefore, we exploited the potential of GIS and remote sensing techniques to calculate the recommended organic amendment requirement for each soil. SOM prediction was performed using a 15 m resolution pan-sharpened Landsat-8 image and an artificial neural network model. Furthermore, we estimated the organic amendments using an approach for a three-year crop rotation (3YCR). In addition, we set a target SOM level content of 1.5%, suitable for the main crops in the study area. The organic amendment was determined at 10% of organic matter over the 3YCR. The produced digital maps were aggregated into homogeneous areas to facilitate interpretation and use by local agricultural advisors. The findings demonstrate that vertisols, isohumic, immature, and fersiallitic soils lose an average of 0.59, 0.77, 1.04, and 1.09 t/ha/year, respectively. Fersiallitic and immature soils lose the most SOM due to their high mineralizing capacity, while vertisols and isohumic soils lose the least due to their low mineralizing potential. The global loss was estimated at an average of 0.80 t/ha/year. To restore the soils to 1.5% of SOM, the results indicate an average amendment of about 31 and 14 t/ha per 3YCR (with returning crop residue) and 47 and 21 t/ha per 3YCR (without returning) for manure and compost application, respectively. Returning crop residue to soil was expected to contribute 4.72 t/ha of SOM per 3YCR on average. Finally, aggregating the results into homogeneous areas could simplify the communication of recommendations while keeping roughly the same results as detailed maps. The adopted method and obtained results highlight the important role of geospatial tools in developing appropriate fertility plans and recommendations for other regions.