Skip to Content
Leveraging Remote Sensing in Data-Limited Regions

Leveraging Remote Sensing in Data-Limited Regions

New Study Shows Effectiveness of Spectral Matching over Machine Learning in Crop Type Mapping

In a recent effort to harness satellite data for countries with limited ground reference information, the International Crops Research Institute for the Semi-Arid Tropics (ICRISAT) conducted a study using Senegal as a model to test various algorithms. While numerous remote sensing products exist for land cover mapping, accurately identifying crop types requires machine learning algorithms to process satellite data. 

This study compares Machine Learning methods with Spectral Matching Techniques (SMTs) and demonstrates that SMTs are more effective than Machine Learning methods in scenarios where ground data are scarce. Although Machine Learning algorithms are valuable for processing satellite images to identify crop types, they require large volumes of high-quality training data. The study emphasizes that SMTs outperformed Machine Learning methods in crop type mapping, particularly where ground data is limited. 

Plot level spatial distribution of crop types in Senegal during cropping season of 2020. Crop type maps derived by Spectral Matching Techniques (SMTs)
Plot level spatial distribution of crop types in Senegal during cropping season of 2020. Crop type maps derived by Spectral Matching Techniques (SMTs)
Dr Murali Gumma, the study’s lead author, stated, “Among the four approaches tested, Spectral Matching Techniques achieved the highest accuracy, exceeding 76%. In contrast, machine learning methods—such as CART (Classification And Regression Tree), SVM (Support Vector Machines), and RF (Random Forest)—which are used for molecular machine learning and predicting compound properties, only reached accuracies between 40% and 55%."

Traditional methods have faced challenges in mapping crop types in small, irregularly shaped fields and regions with inter-cropping practices. This paper highlights that high-resolution satellite imagery when combined with semi-automated algorithms like SMTs is ideally suited for dryland regions in Africa, making it a valuable tool for enhancing agricultural mapping in these challenging environments. 

“In terms of the study's applicability, there is significant potential in West African countries such as Mali and Niger. Improved insights into crop type mapping can be instrumental in calculating agricultural yield and, when combined with weather, climate, and socioeconomic data, can help pinpoint regions where productivity is impacted,” highlighted Dr Stanford Blade, Deputy Director General - Research, ICRISAT.

The Study, Dryland Cropping in Different Land Uses of Senegal Using Sentinel-2 and Hybrid ML Method, was supported by the CGIAR Research Program on Climate Change, Agriculture and Food Security (CCAFS). 

This work aligns with SDGs 2, 11 & 13.

​ ​

For media inquiries, please contact:

Parkavi Kumar
Parkavi Kumar Senior Communications Specialist – Asia
Geo Spatial and Big Data Sciences Resilient Farm and Food Systems Landscapes, Soil Fertility and Water Management Digital Agriculture
About The International Crops Research Institute for the Semi-Arid Tropics

The International Crops Research Institute for the Semi-Arid Tropics (ICRISAT) is a pioneering International Organization committed to developing and improving dryland farming and agri-food systems to address the challenges of hunger, malnutrition, poverty, and environmental degradation affecting the 2.1 billion people residing in the drylands of Asia, Sub-Saharan Africa, and beyond.

ICRISAT was established under a Memorandum of Agreement between the Government of India and the CGIAR on the 28 March 1972. In accordance with the Headquarters Agreement, the Government of India has extended the status of a specified “International Organisation” to ICRISAT under section 3 of the United Nations (Privileges and Immunities) Act, 1947 of the Republic of India through Extraordinary Gazette Notification No. UI/222(66)/71, dated 28 October 1972, issued by the Ministry of External Affairs, Government of India.

Our offices:

Asia: India (Headquarters - Hyderabad)

East and Southern Africa:  Ethiopia, Kenya, Mozambique, Malawi, Zimbabwe

West and Central Africa: Mali, Niger, Nigeria

For all media inquiries, please email: info.comms@icrisat.org

The International Crops Research Institute for the Semi-Arid Tropics
Hyderabad, Telangana, India