Geospatial modeling of future land use and land cover Songkhla Lake Basin, Thailand for sustainable agriculture and forest cover | |
| Author | Himasri, Borra |
| Call Number | AIT Thesis no.RS-18-23 |
| Subject(s) | Geospatial data--Thailand--Songkhla Lake Basin Land cover--Thailand--Songkhla Lake Basin Land use--Thailand--Songkhla Lake Basin Agriculture--Sustainable resources |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Remote Sensing and Geographic Information System, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Abstract | In ongoing decades, the world has encountered uncommon urban development, which imperils the green environment in and around urban regions. Songkhla is a Province of southern Thailand, shares the periphery with Malaysia. We describe the explanatory factors from land- adaptive variables, regional spatial variables and socio-economic variables to simulate future land use. Landsat images of 2000, 2004, 2007, 2011 and 2013 were utilized for Land cover change analysis. To determine the driving factors for land transitions the economic and demographic data of the study area were used. In this, study Multi-Layer Perceptron - Markov Chain (MLP-MC) is used to model Land Use land Cover. The result ofMLP-MC yielded more than 80% of total accuracy to predict the future land use maps. The LU map of 2016 was predicted from all possible periods 2000-2004, 2004-2007, 2007-2013, 2004-2007, 2004-2013, 2007-2013. When the accuracy of all the 2016 predicted maps was calculated with the LU classification Map as reference the predicted map from 2000-2013 period gave the better accuracy result with 89.4% as overall accuracy. This study applied three scenarios from 2016 to simulate Land allocation of 2030 and 2050. The first scenario is Business as usual scenario while second scenario is conversion restriction on Forest conservative lands which are developed based on Master Plan of Songkhla Basin Development for the period 2006-2015 which restricts 88l.96Sq.km of area. Third scenario is Farmland protection Scenario in which Suitable soil for rice farms are restricted for transitions. However, the result of scenario two provided the best result for having the largest amount of forestland after the end of simulation. These outcomes may help to arranging and assessing of land utilize distribution and conserve the potential lands and maintain the sustainable ecosystem in Songkhla Lake Basin. |
| Year | 2018 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Remote Sensing (RS) |
| Chairperson(s) | Tripathi, Nitin Kumar |
| Examination Committee(s) | Virdis, Salvatore G. P. ;Pal, Indrajit ;Hossain, Md. Zakir |
| Scholarship Donor(s) | AIT Fellowship |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2018 |