Land Use Change Detection and Prediction in Upper Siem Reap River, Cambodia

Abstract

Siem Reap River has played a crucial role in maintaining the Angkor temple complex and livelihood of the people in the basin since the 12th century. Land use in this watershed has changed considerably over the last few decades, which is thought to have had an influence on river. This study was carried out as part of assessing the land use and climate change on hydrology of the upper Siem Reap River. The objective was to reconstruct patterns of annual deforestation from 1988 to 2018 and to explore scenarios of land use 40 and 80 years into the future. A supervised maximum likelihood classification was applied to investigate forest cover change in the last three decades. Multi-layer perceptron neural network-Markov chain (MLPNN-MC) was used to forecast land use and land cover (LULC) change for the years 2058 and 2098. The results show that there has been a significantly decreasing trend in forest cover at the rate 1.22% over the last three decades, and there would be a continuous upward trend of deforestation and downward trend of forest cover in the future. This study emphasizes the impacts of land use change on water supply for the Angkor temple complex (World Heritage Site) and the surrounding population.

Applications of the Google Earth Engine and Phenology-Based Threshold Classification Method for Mapping Forest Cover and Carbon Stock Changes in Siem Reap Province, Cambodia

“…Although nearly half of the province is still covered in forest, the quality and value of forest ecosystems has generally declined by about 31% or 322,694 ha in 28 years (Table 8). This decline can be attributed to forest clearing to accommodate an increase in population and new households [66], expansion of Croplands [67], and the government's Economic Land Concession program to promote plantations [68]. Other major drivers of deforestation and degradation were the expansion of agriculture to grow cassava, orchard plantations, and paddy fields [16,47].…”

“…As seen in Figure 8, total FRELs were estimated to be 20,431,376 MgCO 2 for 10 years from 2020 to 2030, which is higher than that projected by Sasaki et al [10] (Figure 9). and new households [66], expansion of Croplands [67], and the government's Economic Land Concession program to promote plantations [68]. Other major drivers of deforestation and degradation were the expansion of agriculture to grow cassava, orchard plantations, and paddy fields [16,47].…”

Predicting Land Cover Change in the Mamminasata Area, Indonesia, to Evaluate the Spatial Plan

“…The land change modeler (LCM) module embedded in TerrSet software (Clark Labs, Worcester, MA, USA) was used in this study. The module developed by Clark Labs analyzes land cover changes, evaluates driving factors, calculates transition potential from one class to another, and builds a model prediction of land cover changes empirically, which can be tested for accuracy [10,18,49,50]. This module has been recognized as an effective tool in predicting land use change, with an easy-to-understand user interface [10].…”

“…In parameter setting, the basic maps (2006 and 2011) and the seven driving-factor maps were first fed into the model to produce a transition potential map, which indicates the probability of change from one class to another by using the MLPNN method [10]. We determined the land cover change by choosing a transition sub-model, which can consist of a single land cover transition or a group of transitions that are thought to have the same underlying driving factors [50].…”

“…As the second step in parameter setting, each driving-factor map was determined as a static or dynamic type. Both types are based on their behavior of change over time [10]. A static variable is a constraint or inhibiting factor for the transition, and does not change over time, while a dynamic variable, such as a development program and infrastructure [10,50], is the driver for transition and is updated during the model run.…”