Dynamics prediction of land use changes using cellular automata and artificial neural network modeling
نویسندگان
1 Research Center for Food Crops, Research Organization for Agriculture and Food, National Research and Innovation Agency, Bogor 16915, Indonesia
2 Research Center for Horticulture, Research Organization for Agriculture and Food, National Research and Innovation Agency, Bogor 16915, Indonesia
3 Research Center for Estate Crops, Research Organization for Agriculture and Food, National Research and Innovation Agency, Bogor 16915, Indonesia
4 Research Center for Food Crops, Research Organization for Agriculture and Food, National Research and Innovation Agency, Bogor 16915, Indonesia
5 Regional Research and Development Planning Agency, Pakpak Bharat Regency, Salak, 22272, Indonesia
6 Department of Agriculture, Deliserdang Regency, Lubuk Pakam, 20518, Indonesia
7 Research Center for Food Crops, Research Organization for Agriculture and Food, National Research and Innovation Agency, Bogor 16915, Indonesia
8 Research Center for Cooperative, Corporation, and People's Economy, Research Organization for Governance, Economy, and Community Welfare, National Research and Innovation Agency, Jakarta 12710, Indonesia
9 Research Center for Cooperative, Corporation, and People's Economy, Research Organization for Governance, Economy, and Community Welfare, National Research and Innovation Agency, Jakarta 12710, Indonesia
doi
10.22034/gjesm.2025.02.04چکیده
BACKGROUND AND OBJECTIVES: Land use change has become one of the main issues in environmental studies and sustainable development at the global level. Although several studies have explored land use change at the regional level, an in-depth understanding of the patterns and drivers of land use change in Pakpak Bharat Regency, North Sumatra, Indonesia, is still very limited. To date, no predictive model can provide long-term insights into land use change trends in the region. The gap in data and analysis can hamper the formulation of effective and sustainable spatial planning policies. Therefore, the study specifically addressing this issue is needed to provide a relevant scientific framework to guide decision-making.METHODS: The study used spatial analysis with cellular automata-artificial neural network or modeling to project and predict land use changes in Pakpak Bharat Regency in 2030. Geographic information system with the Molusce plugin were utilized in this study. The analysis consisted of two stages, namely land use interpretation and land use projection modeling. Primary data was obtained from the field (for soil) and interviews (for the economy) to determine the leading regional commodity. In contrast, secondary data on agroclimate suitability comprised altitude, air temperature data, air humidity, rainfall, wind speed, and duration of sunlight.FINDINGS: Land uses that tended to expand were for plantations/gardens, settlement areas, and Shrubs. Meanwhile, rice fields and mixed vegetation tended to experience a reduction in area over the years. Forest land use tended to fluctuate, increasing in 2018 but decreasing in 2022. Furthermore, the land use prediction for 2030 in Pakpak Bharat Regency showed that land use for forests, rice fields, and Shrubs decreased. On the other hand, land use for plantations, settlements, and fields was projected to increase. The widest durian land suitability class was quite suitable (S2), and thus, durian was recommended to be developed to maintain forests, reduce land damage, and for its high economic value.CONCLUSION: Land use changes in the Pakpak Bharat Regency from 2014 to 2022 were relatively slow. The land use for forests fluctuated between 2014-2018 and 2018-2022, while land uses that consistently increased were for plantations and settlements. The 2022 land use modeling results had an excellent level of accuracy, and thus, the model could be used to predict land use in 2030. In addition, the results showed that durian could become the leading regional commodity because it was scientifically proven to be suitable for plantation and profitable.