Prediction of Soil Quality Index (SQI) and Its Minimum Dataset Indicators for Rice-Based Cropping Systems in the North Bank Plain Zone of Assam

• Published in: Eurasian soil science Vol. 57; no. 10; pp. 1718 - 1729
• Main Authors: Bhuyan, S., Patgiri, D. K., Medhi, B. K., Deka, B., Kandali, G. G., Medhi, S. J., Kalidas-Singh, S., Debnath, A., Zhiipao, R. R., Tsomu, T., Devegowda, S. R., Sandillya, M.
• Format: Journal Article
• Language: English
• Published: Moscow Pleiades Publishing 01.10.2024; Springer Nature B.V
• Subjects: Agricultural Chemistry and Soil Fertility; Cation exchange; Cation exchanging; Cations; Cereal crops; Chemical properties; Chemicophysical properties; Crop yield; Cropping systems; Datasets; Earth and Environmental Science; Earth Sciences; Exchange capacity; Geographic information systems; Geographical information systems; Geotechnical Engineering & Applied Earth Sciences; Indicators; Information systems; Machine learning; Organic carbon; Organic phosphorus; Organic soils; Phosphorus; Porosity; Principal components analysis; Productivity; Rice; Rice fields; Soil; Soil analysis; Soil chemistry; Soil degradation; Soil porosity; Soil properties; Soil quality; Soil surfaces; Soils; Spatial variations; geo-referenced; machine learning; principal component analysis; geographical information system
• ISSN: 1064-2293; 1556-195X
• DOI: 10.1134/S1064229324600854

Prediction of soil quality index is one of the suitable options to determine the productivity of a cropping system. Rice based cropping systems are the most important cropping systems followed in the North Bank Plain region. The productivity of such system has declined continuously due to deterioration of soil quality. The current study was carried out in Cambisols soil to establish soil quality index based on soil physical and chemical properties and identify quality indicators from the rice cropping system. A total of 180 geo-referenced surface soil samples were collected from five rice based cropping systems. The principal components analysis and machine learning model were used to screen the minimum data set indicators for computing the soil quality index. The minimum data set indicators were found as cation exchange capacity, micro aggregate, organic carbon, total porosity and available phosphorus. The SQI for the district ranged from 0.48 to 0.87, with an average of 0.62. The SQI was more significantly positively correlated with the rice equivalent yield of rice potato-based cropping systems, followed by rice rabi vegetables. The spatial variability of the SQI was presented on the geographical information system (GIS) platform through inverse distance weighting (IDW) method of interpolation.