Spatio-temporal analysis of urban-agriculture patterns in Pathumthani using geospatial technologies | |
| Author | Bonthalakoti, Hemanth Sai |
| Call Number | AIT RSPR no.ICT-23-01 |
| Subject(s) | Geographic information systems Machine learnlingLand use--Thailand--Data processing |
| Note | A research study submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Information & Communications Technologies |
| Publisher | Asian Institute of Technology |
| Abstract | This study focuses on the monitoring of Land Use and Land Cover (LULC) changes in Pathum Thani province, Thailand, using Google Earth Engine (GEE) and machine learning algorithms. The region has experienced constant changes due to urban expansion and agricultural intensification. The study utilizes Random Forest (RF), CART, and Naive Bayes (NB) classifiers to identify the changes. Results reveal that RF produced the best overall accuracy with a kappa coefficient of 0.79, while CART had a coefficient of 0.70, and NB had 0.59. The study identifies a significant decrease in agricultural land cover and an increase in scrublands and barren lands. Urban classes were found to be steadily increasing. The findings of the study call for sustainable land use practices in the region and highlight the increasing presence of aquaculture fields in open and scrub land classes in some areas. The study provides essential insights for policymakers and stakeholders interested in maintaining sustainable land use practices in the region. The study also discusses the limitations of using machine learning algorithms, specifically NB, in LULC studies. The study demonstrates the usefulness of GEE and its machine learning algorithms for LULC studies and highlights the importance of selecting the appropriate classifier for improved classification accuracy. Overall, the study contributes to the existing literature on LULC changes in Pathum Thani province, Thailand, and serves as a reference for future research on environmental sustainability and socioeconomic development in the region. Information and communication technologies (ICT) play a crucial role in the integration of remote sensing and GIS for land use and land cover change monitoring. Remote sensing and GIS data are used extensively in land use studies, and the integration of these technologies with ICT allows for more efficient data processing, analysis, and interpretation. This integration can help to improve the accuracy and reliability of land use and land cover maps, as well as provide a more comprehensive understanding of the underlying processes driving land use change. Furthermore, the integration of ICT can enable better data sharing and communication between researchers, policymakers, and other stakeholders involved in land use planning and decision-making. |
| Year | 2023 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information and Communication Technology (ICT) |
| Chairperson(s) | Teerapat Sanguankotchakorn |
| Examination Committee(s) | Mozumder, Chitrini;Vatcharaporn Esichaikul |
| Scholarship Donor(s) | AIT Fellowship |
| Degree | Research report (M. Eng.) - Asian Institute of Technology, 2023 |