BIG DATA CONCEPT ANALYSIS FOR AGRICULTURAL SUITABLE LAND GEOGRAPHIC INFORMATION SYSTEM APPROACH

Abstract

Big data analysis for agriculture provides farmers with a comprehensive view of the concept of increasing agricultural productivity using the effectiveness of irrigation canals, predicting rainfall to determine outcrop patterns, and identifying the adequacy of agricultural land. It also allows farmers to optimize irrigation, increasing yields while reducing costs and environmental impact. It also will enable farmers to optimize irrigation; Rainfall predictions are used to determine cropping patterns and identify suitability for permits. It can also be used to deal with weather patterns and climate change, allowing farmers to adapt their practices to reduce the impact of climate change, ultimately protecting their crops and currency. This research aims to develop plant productivity through several stages of research and the use of methods. The methods used in this study are 1)Prediction of water discharge using the linear regression method; 2)Prediction of Rainfall for Planting Pattern Training using the SARIMA method, and 3)Suitability of Agricultural Land using the Cluster Area Analysis Approach. The results of this study are that in the Sleman region, the adequacy of water for agricultural areas is in the excellent category (fulfilled), cropping pattern spending is divided into 2, namely dry and wet months. In the wet months (high rainfall), rice is suitable for planting from January to May; for the dry months between June and October, tobacco, soybeans, corn, peanuts, green beans, cassava, and sweet potatoes. As for land suitability, it consisted of 46025.36 Ha (81%) suitable and 10811.48 Ha not suitable for use.