Integrated Use of Optical and Radar Data for Cropland Mapping Over the Mountain Slope Area in Boyolali, Indonesia

Abstract

Mapping agricultural land cover data is important as an effort to support national food security, especially in Boyolali, Central Java Province, Indonesia which is one of the national rice granaries. However, mapping in the mountain slope area using optical data only is challenging due to cloud cover. The development of remote sensing technology has encouraged the possibility to integrate data with different sensors. This data integration is needed to optimize the ability to detect and map cropland that has a variety of characteristics. Therefore, this study aims to identify the cropland through the integration of time-series optical and Synthetic Aperture Radar (SAR) data. Detection of cropland was carried out using 2021 data. Polarisation of VV, VH, and ratio of VV/VH data was derived from the Sentinel-1, whereas image indices of Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Soil Adjusted Vegetation Index (SAVI) data were obtained from Sentinel-2. Data of Sentinel-1 and Sentinel-2 was combined and several features were selected based on their importance score. Random Forest (RF) classification was then performed. The result show that the mapping using integrated data could improve the accuracy. This indicates the possibility of data to be implemented in further studies such as the cropland type mapping and the estimation of food productivity.

Assessment of Soil Degradation for Biomass Production in Tanjungpinang, Indonesia

“…Soil degradation potential can be measrured by combining field measurement and geographic information system (GIS) analysis. GIS can help to analyze and create model by using spatial data in large area such as in regency or broarder scale (13)(14)(15). By using GIS, all of soil properties paramater map can be analyze to produce a soil degradation map used theoverlay tool.…”

Land Use Change Modelling Using Logistic Regression, Random Forest and Additive Logistic Regression in Kubu Raya Regency, West Kalimantan

“…Land use change analysis can be completed by building a model. The land use change model may facilitate the understanding of the process of land use change and its driving factors (Bohai et al, 2023;Cao et al, 2023;Danardono, et al, 2021;Fikriyah, et al, 2023). In addition, the model can be used to predict changes in land use and land cover by means of a simulation process based on a geographic information system using a statistical machine learning approach.…”