GIS-based fuzzy membership model for crop-land suitability analysis

Crop-land suitability analysis is a prerequisite to achieve optimum utilisation of the available land resources for sustainable agricultural production. The Food and Agricultural Organisation [FAO, 1976. A framework for land evaluation (Soils Bulletin No. 32). FAO, Rome.] recommended an approach for land suitability evaluation for crops in terms of suitability ratings from highly suitable to not suitable based on climatic and terrain data and soil properties crop-wise. The assignment of a given area element (pixel) to any one suitability class is encountered with problems due to the variation of soil properties within the area as well as matching of the soil properties with more than one suitability class to different extents. The Boolean methods are designed to assign a pixel to a single class and no provision exists for assigning partial suitability to each of the appropriate suitability classes. In the present study the use of fuzzy (partial) membership classification is used to accommodate the above uncertainty in assigning the suitability classes to the pixel. The evaluation of the spatial variability of relevant terrain parameters is carried out in a geographic information system environment while assigning the land suitability for crops in the study area of Kalyanakere sub-watershed in Karnataka. Nine parameters (eight of soil and one of topography) are considered and suitability analysis is carried out by fuzzy membership classification with due weightage factors included to accommodate the relative importance of the soil parameters governing the crop productivity. According to the field information, the crop being grown in maximum area is finger millet. However, the crop-land evaluation results of the present study reveal that maximum area is potentially suitable for growing ground nut.