Title: IMPROVEMENT OF TRADITIONAL AND HYBRID INTERPOLATION TECHNIQUES USING SUPPORT VECTOR MACHINE FOR LAND SURFACE TEMPERATURE ANALYSIS IN URBAN AREAS
<br>Cover Date: 2025-03-01
<br>Cover Display Date: March 2025
<br>DOI: 10.21163/GT_2025.201.21
<br>Description: Interpolation techniques are highly effective numerical methods for achieving comprehensive spatial data coverage without the need to measure data at every location within the study area. Traditional interpolation methods, such as Inverse Distance Weighted (IDW) and Kriging, are numerical computations that rely on mathematical models without considering environmental influences on the spatial factors being interpolated. On the other hand, Support Vector Machines (SVM) are machine learning algorithms designed to enhance the accuracy of numerical computations. This research aims to improve and compare traditional interpolation techniques, specifically IDW, Ordinary Kriging (OK), and OK + SVM. The latter technique combines the OK interpolation concept with SVM learning to classify land cover and weight the interpolation of spatial data related to Land Surface Temperature (LST) in urban areas. The study revealed that the IDW technique produced values of Tmax and Tmin that were the closest to the actual measured values, followed by OK + SVM and OK, respectively. Furthermore, when assessing the interpolated data from 1,650 points extracted from LST using each technique against statistical tests such as MAE, MSE, and RMSE, it was found that OK + SVM provided better results than IDW and OK. Therefore, OK + SVM enhances interpolation accuracy by incorporating land cover classification, outperforming IDW and OK in LST estimation.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: ENHANCING TOURIST EXPERIENCE: A FUZZY TOPSIS APPROACH TO DESTINATION RECOMMENDATION SYSTEMS
<br>Cover Date: 2025-01-01
<br>Cover Display Date: 2025
<br>DOI: 10.30892/gtg.58120-1405
<br>Description: To promote tourism effectively, it is essential to drive flexibility and sustainable growth within the sector. This requires a multi-faceted approach involving various organizations, as well as the development of systems that assist tourists in decision-making. The objective of this research is twofold: (1) to develop a recommendation system based on Fuzzy TOPSIS that integrates data from expert opinions, tourist behavior, and survey feedback, and (2) to design a system that enables tourists to make personalized destination choices through a recommendation process that accommodates diverse user preferences. This research employs a Multi-Criteria Decision Analysis (MCDA) approach using Fuzzy TOPSIS, leveraging survey data collected from 250 respondents, including tourism experts and visitors in Maha Sarakham province. The survey evaluated ten key criteria influencing destination selection, such as accessibility, safety services, and the availability of cafés and coffee shops. Accessibility and safety services emerged as the most critical factors, both receiving the highest scores of 9, while dining options also scored highly with a rating of 7. Conversely, criteria such as shuttle services and proximity to po lice stations were deemed less significant. According to the Fuzzy TOPSIS analysis ranked Phra That Na Dun, Wat Puttha Wanaram, and the Phra Yuen Mongkhon Buddha Image as the top three attractions, showcasing their strong alignment with tourist preferences. Lower-ranked sites, such as Ban Chiang Hian Museum and Chi Long Forest Park, highlight opportunities for development through infrastructural improvements and enhanced marketing efforts. The system’s user satisfaction evaluation demonstrated favorable results, with high ratings for decision-making capability (4.67) and ease of use (4.67), reflecting the system’s ability to align recommendations with user preferences effectively. Quantitative evaluations of the system yielded a precision of 85%, recall of 80%, and an F1-score of 82.42%, indicating a balanced performance in delivering accurate and relevant recommendations. Furthermore, the integration of Fuzzy MCDA with user-centered design ensures that the recommendation system remains adaptable to evolving tourist preferences. This framework demonstrates the importance of integrating flexible, user-centered recommendations into tourism to meet evolving visitor needs effectively.
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: ESTIMATION OF ABOVE-GROUND BIOMASS USING HYBRID MACHINE LEARNING BASED ON SATELLITE IMAGRY
<br>Cover Date: 2024-12-01
<br>Cover Display Date: December 2024
<br>DOI: N/A
<br>Description: This paper assesses the performance of different machine learning algorithms, specifically decision tree, support vector machines, k-nearest neighbors, and a hybrid model that integrates these techniques in estimating aboveground biomass (AGB) using remote sensing and field data. Vegetation indices derived from Sentinel-2A satellite imagery, such as NDVI, RVI, SAVI, and TNDVI, were analyzed for their correlation with AGB. The results indicated that while these indices provide valuable insights into vegetation health, their correlation with AGB is relatively weak. The hybrid model, which combines DT, SVM, and kNN, outperformed individual models, achieving the lowest RMSE (0.389), highest R² (0.803), and lowest MAE (0.287), thus providing the most accurate and reliable predictions of AGB. The geographic spread of AGB estimates indicated that the hybrid model produced more consistent and constrained estimates, emphasizing its robustness. These findings highlight the hybrid machine learning approach as a promising tool for improving the precision and reliability of AGB estimates, which is crucial for forest carbon storage assessment and ecological health monitoring. Future research should focus on incorporating data from other remote sensing platforms and exploring advanced machine learning algorithms to further enhance predictive performance.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: ESTIMATION OF ABOVE-GROUND CARBON SEQUESTRATION IN THE NATIONAL RESERVED FOREST USING VEGETATION INDICES AND GRADIENT BOOSTING MACHINE LEARNING
<br>Cover Date: 2024-09-01
<br>Cover Display Date: September 2024
<br>DOI: N/A
<br>Description: The aim of this research is to calculate the amount of above ground carbon (AGC) sequestration in the National Reserved Forest using vegetation indices and gradient-boosting machine learning. Study operation 1 Set 16 sample plots with the size of 40×40 meters, then measure the girth and all trees’ height in the plot and calculate the estimation of AGC sequestration using allometric equations, and 2) Analyze the estimation of AGC sequestration using vegetation indices and gradient-boosting machine learning. The result finds that there are 2,186 plants in 33 types. Analysis result for the estimation of AGC sequestration using allometric equations finds that the study area has carbon sequestration of 44.14 tC and the density analysis using Inverse Distance Weight (IDW) finds that the spatial carbon density of 3,180.179 tC. Analysis results for the estimation of AGC sequestration using vegetation indices and gradient-boosting machine learning finds that the sum of carbon in the area is 2,855.18 tC. Statistical analysis of such data finds that the correlation coefficient is 0.964.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Enhanced Rubber Yield Prediction in High-Density Plantation Areas Using a GIS and Machine Learning-Based Forest Classification and Regression Model
<br>Cover Date: 2024-09-01
<br>Cover Display Date: September 2024
<br>DOI: 10.3390/f15091535
<br>Description: Rubber is a perennial plant grown for natural rubber production, which is used in various global products. Ensuring the sustainability of rubber cultivation is crucial for smallholder farmers and economic development. Accurately predicting rubber yields is necessary to maintain price stability. Remote sensing technology is a valuable tool for collecting spatial data on a large scale. However, for smaller plots of land owned by smallholder farmers, it is necessary to process productivity estimates from high-resolution satellite data that are accurate and reliable. This study examines the impact of spatial factors on rubber yield and evaluates the technical suitability of using grouping analysis with the forest classification and regression (FCR) method. We developed a high-density variable using spatial data from rubber plots in close proximity to each other. Our approach incorporates eight environmental variables (proximity to streamlines, proximity to main river, soil drainage, slope, aspect, NDWI, NDVI, and precipitation) using an FCR model and GIS. We obtained a dataset of 1951 rubber yield locations, which we split into a training set (60%) for model development and a validation set (40%) for assessment using area under the curve (AUC) analysis. The results of the alternative FCR models indicate that Model 1 performs the best. It achieved the lowest root mean square error (RMSE) value of 19.15 kg/ha, the highest R-squared (R<sup>2</sup>) value (FCR) of 0.787, and also the highest R<sup>2</sup> (OLS) value of 0.642. The AUC scores for Model 1, Model 2, and Model 3 were 0.792, 0.764, and 0.732, respectively. Overall, Model 4 exhibited the highest performance according to the AUC scores, while Model 3 performed the poorest with the lowest AUC score. Based on these findings, it can be concluded that Model 1 is the most effective in predicting FCR compared to the other alternative models.
<br>Citations: 3
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Thailand’s Urban Forestry Programs Are Assisted by Calculations of Their Ecological Properties and Economic Values
<br>Cover Date: 2024-09-01
<br>Cover Display Date: September 2024
<br>DOI: 10.3390/land13091440
<br>Description: Forests are the largest carbon sinks in the world. They play a crucial role in mitigating climate change through carbon storage. Assessing carbon storage in forests is essential for policy formulation, management planning, and as a strategy to reduce the impacts of global warming. The aims of this research were to explore plant diversity, assess tree biomass, and evaluate carbon storage and carbon credits in urban forestry areas under the Thailand Voluntary Emission Reduction Program (T-VER). The study was conducted in the forested area of Rajamangala University of Technology Isan, Surin Campus, Thailand, and encompassed 60.96 ha. The methodology involved the creation of 10 temporary sample plots, each measuring 40 × 40 m. We then surveyed the species types and measured tree diameter at breast height (DBH) and the total height. Biomass was calculated using allometric equations and the stored carbon was quantified. In this study, we identified 85 species of plants. The analysis of tree biomass averaged 23,1781.25 kg/ha or 231.81 ton/ha. The carbon storage was estimated to be 108.94 tC/ha. When aggregating the data for the entire project, the total carbon storage amounted to 6851.55, with an equivalent carbon sequestration capacity of 25,122 tCO<inf>2</inf>e in the base year (baseline). We calculated that the carbon storage capacity could increase to 28,741.00 tCO<inf>2</inf>e with proper maintenance of the urban forest area over a 10-year period, equivalent to a carbon sequestration capacity of 3619 tCO<inf>2</inf>e. This would result in a carbon credit value equivalent to USD 90,475.
<br>Citations: 2
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Spatial Predictive Modeling of Liver Fluke Opisthorchis viverrine (OV) Infection under the Mathematical Models in Hexagonal Symmetrical Shapes Using Machine Learning-Based Forest Classification Regression
<br>Cover Date: 2024-08-01
<br>Cover Display Date: August 2024
<br>DOI: 10.3390/sym16081067
<br>Description: Infection with liver flukes (Opisthorchis viverrini) is partly due to their ability to thrive in habitats in sub-basin areas, causing the intermediate host to remain in the watershed system throughout the year. Spatial modeling is used to predict water source infections, which involves designing appropriate area units with hexagonal grids. This allows for the creation of a set of independent variables, which are then covered using machine learning techniques such as forest-based classification regression methods. The independent variable set was obtained from the local public health agency and used to establish a relationship with a mathematical model. The ordinary least (OLS) model approach was used to screen the variables, and the most consistent set was selected to create a new set of variables using the principal of component analysis (PCA) method. The results showed that the forest classification and regression (FCR) model was able to accurately predict the infection rates, with the PCA factor yielding a reliability value of 0.915. This was followed by values of 0.794, 0.741, and 0.632, respectively. This article provides detailed information on the factors related to water body infection, including the length and density of water flow lines in hexagonal form, and traces the depth of each process.
<br>Citations: 4
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: ESTIMATION OF SOLAR POTENTIAL AND URBAN LAND USE CLASSIFICATION USING SATELLITE IMAGERY AND DIGITAL SURFACE MODELS
<br>Cover Date: 2024-03-01
<br>Cover Display Date: March 2024
<br>DOI: N/A
<br>Description: This study aims to estimate the solar potential of a given area by integrating urban land-use data from Sentinel-1 imagery and digital surface models (DSM) using the Solar Radiation tool. Solar irradiation exhibits temporal variations influenced by climatic conditions and the location of the sun. Accurate prediction of solar radiation is crucial for decision-making in renewable energy and urban planning. The Random Forest algorithm is employed for urban land use classification, providing reliable results in distinguishing different land use categories, especially urban areas. Evaluation metrics such as branching factor, miss factor, urban detection percentage, and quality percentage assess the performance of the classification model. The estimation of solar potential maps allows for the identification of areas with high solar energy potential, facilitating site selection for solar energy installations. The study highlights the challenges of calibrating atmospheric parameters and emphasizes the importance of considering key inputs such as atmospheric transmission, elevation, slope, and orientation in the Solar Radiation tool for accurate calculations. The findings contribute to understanding solar potential mapping, remote sensing applications in urban land use analysis, and inform decision-making for sustainable development and renewable energy utilization.
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: An Empirical Analysis of Above-Ground Biomass and Carbon Sequestration Using UAV Photogrammetry and Machine Learning Techniques
<br>Cover Date: 2024-01-01
<br>Cover Display Date: 2024
<br>DOI: 10.1109/ACCESS.2024.3514074
<br>Description: This research aims to analyze above-ground biomass and carbon sequestration using unmanned aerial vehicle (UAV) photogrammetry and machine learning methods, focusing on a case study of the dry dipterocarp forest in the Ban Hin Lat and Hin Lat Phatthana Community Forests. The methodology involved conducting field surveys and data analysis to estimate biomass using allometric equations and UAV photogrammetry data. The estimated biomass from both methods was then analyzed to determine carbon sequestration. Field survey results identified a total of 1,241 trees across 39 species. The analysis using allometric equations found a total above-ground biomass of 454,310.54 kg (454.31 tons), with a carbon sequestration of 213,525.95 kgCO2e (213.52 tCO2e). In contrast, the machine learning analysis using the Deepness technique from UAV data estimated an above-ground biomass of 463,689.13 kg (463.68 tons), with a carbon sequestration of 217,933.89 kgCO2e (217.93 tCO2e). The difference in carbon sequestration estimates between field data and UAV photogrammetry was 4.4 tons, indicating a relatively low error margin of 9.39%. Additionally, the results for the assessment data across different histogram intervals revealed a detection accuracy of tree crowns using UAV photogrammetry at 0.594, with a precision of 0.798, recall of 0.699, and F1 score of 0.745.
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Estimates of PM2.5 Concentration Based on Aerosol Optical Thickness Data Using Ensemble Learning with Support Vector Machine and Decision Tree
<br>Cover Date: 2023-12-22
<br>Cover Display Date: 22 December 2023
<br>DOI: 10.5755/j01.erem.79.4.33913
<br>Description: Air pollution, particularly fine particulate matter with a diameter of 2.5 micrometers or less (PM2.5), is a significant public health concern in many regions worldwide, including the northeastern region of Thailand. This study investigates the correlation between PM2.5 concentrations and meteorological spatial datasets such as surface relative humidity (SRH), surface wind speed (SPD), visibility (Vis), surface temperature (ST), and aerosol optical thickness (AOT) in the region. GIS techniques and the inverse distance weighting technique were used to create spatial maps of the meteorological datasets and ground station PM2.5 measurements. Pearson correlation analysis was performed to examine the relationship between PM2.5 and the meteorological datasets. Decision tree and support vector machine (SVM) algorithms were employed to estimate PM2.5 concentrations based on the spatial datasets. The results showed that Vis and ST have a moderate positive linear relationship with PM2.5, while AOT has a moderate negative linear relationship. SRH and SPD have weak relationships with PM2.5. The decision tree and SVM algorithms demonstrated a strong positive correlation between estimated and measured PM2.5 concentrations. The study shows that machine learning algorithms can be effective tools for estimating PM2.5 concentration based on AOT data, and feature selection can improve model performance. Ensemble learning could be employed to further improve model performance, particularly in regions with high spatial variability. Overall, the study provides a promising approach for estimating PM2.5 concentration using machine learning algorithms and AOT data.
<br>Citations: 3
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: The Carbon Sequestration Potential of Silky Oak (Grevillea robusta A.Cunn. ex R.Br.), a High-Value Economic Wood in Thailand
<br>Cover Date: 2023-09-01
<br>Cover Display Date: September 2023
<br>DOI: 10.3390/f14091824
<br>Description: Silky Oak or Silver Oak (Grevillea robusta A.Cunn. ex R.Br.) is classified as a high-value economic wood in Thailand, it is also considered to be a plant that can grow rapidly, and it has the potential to efficiently reduce greenhouse gases emitted into the atmosphere. This research aimed to study and develop an allometric equation to evaluate the biomass of F1 Silky Oak, which was imported to Thailand from Australia, and grown in Thailand’s economic woods in Silky Oak sites in Pak Chong District, Nakhon Ratchasima Province. The sample group consisted of trees of different ages (i.e., of 2 years, 3–4 years, and 7 years). An allometric equation was used to determine the tree biomass, based on mathematical models that describe the relationship between tree biomass and diameter at breast height (DBH). It was developed in the form of a quadratic equation by multiplying the square DBH by the total height (DBH<sup>2</sup> × Ht). Subsequently, the equation was separated into different components, which corresponded with different parts of the tree (i.e., stem, branches, leaves, and roots). The following equations were obtained for the stem: Ws = 0.0721 (D<sup>2</sup>H) 0.8297 R<sup>2</sup> = 0.998. The following equations were obtained for the branches: Wb = 0.0772 (D<sup>2</sup>H) 0.7027 R<sup>2</sup> = 0.977. The following equations were obtained for the leaves, Wl = 0.2085 (D<sup>2</sup>H) 0.4313 R<sup>2</sup> = 0.990. The following equations were obtained for the roots: Wr = 0.3337 (D<sup>2</sup>H) 0.4886 R<sup>2</sup> = 0.957. The results of a laboratory elemental analysis of the carbon sequestration in the biomass, using a CHN elemental analyzer, showed that the mean percentage of carbon content in the stems, branches, leaves, and roots was 45.805. Applying the developed allometric equation for evaluating carbon sequestration, using the survey data from the sample sites of Silky Oak, it was found that the amount of carbon sequestration for the aboveground biomass in three sites was 130.63 tCO<inf>2</inf>eq. When the amount was converted into carbon dioxide, which was absorbed in the three sites, we obtained a value of 478.99 tCO<inf>2</inf>eq. The results of the application of the allometric equation showed that there was substantial carbon sequestration potential in the surveyed sites, emphasizing the role of Silky Oak plantations for climate change mitigation and sustainable land management. This study advances our understanding of Silky Oak growth and carbon storage dynamics, offering valuable tools for biomass estimation and promoting environmentally beneficial land use practices.
<br>Citations: 7
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: APPLICATION OF A MULTI-LAYER PERCEPTRON NEURAL NETWORK TO SIMULATE SPATIAL-TEMPORAL LAND USE AND LAND COVER CHANGE ANALYSIS BASED ON CELLULAR AUTOMATA IN BURIRAM PROVINCE, THAILAND
<br>Cover Date: 2023-05-01
<br>Cover Display Date: 1 May 2023
<br>DOI: 10.30638/eemj.2023.074
<br>Description: This study aimed to analyze the land use/land cover (LULC) changes of Mueang Buriram district, Buriram province, Thailand, using LULC data from 2011, 2016, and 2021. The transition potential model based on a multi-layer perceptron neural network and cellular automata was used to predict the LULC changes, taking into account the distance from the road, institutional land, forests, and elevation. The results showed that paddy fields (A1) were the dominant LULC class throughout the study period, and the transition potential model indicated that forests played a crucial role in determining LULC changes. The spatial-temporal change analysis predicted the LULC changes for 2021, 2026, and 2031, showing a slight increase and decrease in different LULC classes, with paddy fields (A1) increasing by 0.027% from 2021 to 2031. The findings of this study have theoretical and practical implications for understanding the spatial and temporal dynamics of LULC changes in Mueang Buriram district and could aid in developing sustainable land use policies and practices to address the challenges of urbanization and environmental conservation in the study area.
<br>Citations: 5
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: UTILIZING GIS AND REMOTE SENSING FOR MODELING THE SPATIAL DISTRIBUTION OF WILD ORCHID SPECIES IN PHU FAEK FOREST PARK
<br>Cover Date: 2023-01-01
<br>Cover Display Date: 2023
<br>DOI: 10.30892/gtg.50417-1135
<br>Description: Thailand's wild orchids, cherished for their beauty, face threats from habitat loss and over-collection. Urgent conservation is needed, with efforts including protected areas and sustainable practices. This study aims to model the distribution of wild orchids through the utilization of remote sensing and GIS techniques. The methodology involves comprehensive surveys of wild orchid species within Phu Faek forest park. Spatial regression analysis explores intricate relationships between wild orchid density and environmental factors such as NDWI, forest type, elevation, basin density, and aspect. The results of field surveys identified 28 orchid species with diverse distribution patterns, including dominant species like Aerides falcata Lindl. & Paxton, Aerides falcata Lindl., and Cleisostoma fuerstenbergianum F.Kranzl. The spatial regression model revealed distribution patterns, with higher density in central and north regions. The NDWI indicator, which reflects moisture content, provided additional insights into the distribution of orchids
<br>Citations: 1
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: GEOGRAPHICALLY WEIGHTED REGRESSION MODELLING FOR ABOVE-GROUND BIOMASS ASSESSMENT FROM SATELLITE IMAGERY IN TAD SUNG WATERFALL PARK FOREST, THAILAND
<br>Cover Date: 2022-04-01
<br>Cover Display Date: 1 April 2022
<br>DOI: N/A
<br>Description: The estimate of carbon sequestration in terms of above-ground biomass (AGB) within the tree from the high-resolution image. The objective of this paper to assessment of AGB in Tad Sung Waterfall park forest in Kalasin province, Thailand. The allometric equations used to calculate the AGB from field measurement of 62 samples plot, by each plot has a dimension of 40m × 40 m. The normalized difference vegetation index (NDVI), soil-adjusted vegetation index (SAVI), and Fractional vegetation cover (FVC) from the satellite imagery was use to assessment of AGB using the geographically weighted regression (GWR) model. The results The results found that the total number of 4682 trees in the 62 sample plots and the calculated the AGB of the tree in the sample plot using the allometric equation was 79.6 Ton per hectare. The results of spatial analysis of AGB base on GWR found that the R<sup>2</sup>value of the global regression and GWR model were 0.366 and 0.856, respectively and the optimal bandwidth estimation for GWR in this study was 48.78. The adjusted R<sup>2</sup>values of the GWR model achieved a significant improvement in the global regression from 0.108 to 0.59.
<br>Citations: 3
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Forecasting time series change of the average enhanced vegetation index to monitoring drought condition by using Terra/Modis data
<br>Cover Date: 2021-12-15
<br>Cover Display Date: 15 December 2021
<br>DOI: 10.17707/AgricultForest.67.4.10
<br>Description: Drought condition is a natural disaster that has caused economic and social damages considerably including a shortage of consuming water, and has been a hindrance to the agricultural production and industrial development. Currently, the drought condition tends to be more severe in Yasothon Province of Thailand, thus affecting plantation in the area. The purpose of this study was to monitor the drought condition of Yasothon Province, which is located in the Northeastern region of Thailand, by using Enhanced Vegetation Index (EVI) data during 2010 – 2019 obtained from Terra/Modis Satellite, and by studying the change in time series from the average EVI during 2010 – 2019, for the forecast in 2020 – 2022 by using moving averages method and exponential smoothing method in order to compare the differences between the original data of average EVI and the data of average EVI adjusted by smoothing algorithm using RMMEH method. Statistics used in examining the forecasting accuracy were MAD and MAPE. It was found from the study that MAD and MAPE of the forecast of the original average EVI and the average EVI adjusted by using RMMEH method were slightly different in that the average EVI adjusted by using RMMEH method and forecasted by moving averages method was best accurate. In addition, according to the time series change forecast of EVI, it was found that the original average EVI and the EVI which was smoothed by RMMEH method of the forecasting year during 2020 – 2022 by using moving average method and exponential smoothing method were very low in each year, indicating that the drought would occur in the future.
<br>Citations: 9
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Artificial neural networks for the classification of shrimp farm from satellite imagery
<br>Cover Date: 2021-10-01
<br>Cover Display Date: October 2021
<br>DOI: 10.21163/GT_2021.162.12
<br>Description: Shrimp production was the high demand for the popular in the global market in Thailand. The change of land use is important for the management and monitoring of land use changed. The objectives of this paper to (1) classification of shrimp farm using artificial neural networks (ANN) technique from the Sentinel-2 imagery. (2) change detection of land use changes map among 2015, 2018, and 2020. The land use classification based on ANN technique and the accuracy assessment by used the confusion matrices and kappa coefficient. The classify of land use classes divide into built-up, forest, water bodies, paddy field, shrimp farm, and field crop. The change detection methods used was the image differencing technique was performed to the land use changes map. The result of land use classification show that the field crop area was 80% cover the most area. The result of land use changed show that built-up, paddy field, and shrimp farm increased throughout between year 2015 to 2020. The shrimp farm between year 2015 to 2020 to increasing trend of related with the shrimp production was the high demand for the popular in the global market.
<br>Citations: 3
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Parking site selection for light rail stations in Muaeng district, Khon Kaen, Thailand
<br>Cover Date: 2020-06-01
<br>Cover Display Date: June 2020
<br>DOI: 10.3390/sym12061055
<br>Description: Khon Kaen District is in the central, north-east part of Thailand and is being developed to handle the country’s growth. Khon Kaen District is undertaking the project of building a light rail as a facility for the people. Consequently, one of the problems is ensuring adequate parking for people using the light rail service. In general, the symmetry concept naturally used in decision making to finding an optimal solution for decision and optimization problems. In this paper, multi-criteria decision analysis (MCDA) and multi-objective decision making (MODM) were used to solve the parking site selection problem, which made the decision easier. This paper proposed an analytic hierarchy process (AHP) technique, combined with the geographical information system (GIS), to evaluate the weight of the criteria used in the analysis and find potential parking solutions. Furthermore, this paper proposed the application of a linguistic technique with fuzzy TOPSIS methods to analyze the appropriateness of parking site selections from potential candidates to support use of the light rail. The results of the MCDA show that the most suitable parking lot location is along the light rail and closest to the business area. The results of the fuzzy TOPSIS method, both positive and negative ideal decisions, can help inform decision makers in selecting which candidate site is optimal for parking.
<br>Citations: 12
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Spatial urban land use planning using multi-objective optimization and genetic algorithm
<br>Cover Date: 2020-01-01
<br>Cover Display Date: 2020
<br>DOI: N/A
<br>Description: Urban planning requires not only estimating and locating the future urban extent but also balancing planning aspects to achieve objectives and comply with constraints. The better planning should be able to compromise the multiple conflicting demands from different aspects. The aim of this study focuses on developing and simulating a procedure for optimal urban class planning using Genetic algorithm and Multi-objectives decision analysis (GA-MODA) in plot level. Resulting plans of 2016 were compared to existing land use. The methods were employed to operate on 2 case areas which were selected from a part of Nakhon Ratchasima town. GA-MODA process was applied to generating a number of representative plans that meet the requirement of 6 given objectives and 7 constraints. The objectives cover sufficient housing, employment, open green area, high compatibility, and minimized changing cost and travel rate. For better living, constraints were setup to comply with suggested areas and population densities of urban classes. GA-MODA process resulted in 26 and 370 plans for case areas. These plans were compared to existing land use. The comparison revealed that constraint compliance, being at Pareto front, and sums of normalized objective values (SNOV) of GA-MODA plans are better than of existing land use. It indicates that GA-MODA urban planning is a capable method to generate a number of optimal plans which can provide a better quality of living than existing land use.
<br>Citations: 2
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: WebGIS for managing household data within a provincial big data project
<br>Cover Date: 2019-07-27
<br>Cover Display Date: 27 July 2019
<br>DOI: 10.1145/3348445.3348479
<br>Description: The government agencies require decision support information before commencing their community development projects in rural areas. However, such information is not always available or does not meet their requirements. This research presents the design and development of the WebGIS, which is intended to store and provide spatially related household information for government agencies. This research has been conducted as a part of a provincial big data project. In this research, the spatial database system and the data visualization of the database were designed and developed by focusing on the details of each house in the targeted villages. The data were collected by the researchers from the study areas, which comprised 5 villages in Loei and Khonkaen Provinces in Thailand. The important household and location data were collected and combined with the community data from the Community Development Office. The GIS was developed using QGIS where the geolocation of each house in the villages was applied on the map derived from Google map. The data were analyzed and visualized in different formats such as color, table, and graph in order to establish the data classification and summarization. The system and data were finally evaluated by the Community Development Office and community leaders in terms of system performance and data accuracy.
<br>Citations: 2
<br>Aggregation Type: Conference Proceeding
<br>-------------------
<br><br><br>Title: Change vector analysis using integrated vegetation indices for land cover change detection
<br>Cover Date: 2018-10-01
<br>Cover Display Date: October-December 2018
<br>DOI: N/A
<br>Description: The change detection is the process to identify the difference of area between two dates in the same location. The objective of this research is to study the land cover change from satellite image during the years 2007 and 2017 using change vector analysis (CVA). The normalized difference vegetation index (NDVI) and bare soil index (BI) were the parameters considered for land cover change analysis using the CVA. The magnitude and direction of change vectors were used to identify of land cover change. Data collection was conducted by interviewing group leader of 3 sub-districts where considerable land cover changes were observed to evaluate the land cover changes using GIS. The results of the magnitude of change vector have revealed no change 52 % and change 48 %. The results of the direction of change vector found that the moisture change more than 76 %. The land cover change from questionnaire show that Thakhonyang, and Khamriang subdistricts have changed from agriculture area to built-up area, butMakha sub-district did not show changes.
<br>Citations: 8
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Application of remote sensing technology for drought monitoring in Mahasarakham Province, Thailand
<br>Cover Date: 2016-01-01
<br>Cover Display Date: 2016
<br>DOI: N/A
<br>Description: Drought, a natural phenomenon, has been found often in Mahasarakham province. It has impact on vegetation in the area. Due to the reason, the objective of the study is to develop a methodology to detect drought in the area using vegetation spectrum in different periods of the satellite passing over the area in Mahasarakham province, approximately 5,291.6830 sq.hn. The Normalized Vegetation Index (NDVI) obtained from the Modis data has been used in order to detect the vegetation condition in the study area. In addition, the Standardized Vegetation Index (SVI) was used to examine the area with the NDVI difference from the average value of NDVI in the same period. This can reflect the drought through the vegetation index. However, the study has discovered that in the year 2010, the drought in the area was the most severe. The second and the third most severe droughts occurred in 2007 and 2012 respectively. The study has deployed the analyzing technique and the formation of drought according to spatial and time factors. Different satellite images obtained from the Modis data revealed the formation and type of droughts effectively. This will be useful for the preparation of the drought mitigation in the area for concern agencies.
<br>Citations: 30
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>Title: Weighting parameters to improve IHS transformation in data fusion of THEOS imagery
<br>Cover Date: 2014-12-01
<br>Cover Display Date: 1 December 2014
<br>DOI: N/A
<br>Description: To efficiently fuse multi-spectral (MS) and panchromatic (PAN) images acquired from THEOS satellite, the authors offer proper parameters to improve IHS fusion technique based on its spectral responsivity. This concept was originally contributed by Tu et al., applied to IKONOS image fusion. Red and NIR bands of THEOS imagery with lower response were adjusted to be higher and close to the response of PAN band using those new proposed parameters. Indexes including the correlation coefficients (CCs), relative dimensionless global error in synthesis (ERGAS), and relative average spectral error (RASE) of the pan-sharpened and MS images were compared to quantitatively evaluate the quality of pansharpened images. The resulting indexes indicate that the quality of pan-sharpened images obtained from the study be obviously high. Indexes from images transformed by the method of Tu et al. were compared to the indexes obtained from the study as well. The comparison expresses that indexes resulted from the study are better than ones using the method of Tu et al. It can confirm that the fusion method based on the concept of adjustment on spectral responsivity of specific sensor is valid. The new approach provides a satisfactory result of image fusion, both visually and quantitatively.
<br>Citations: 0
<br>Aggregation Type: Journal
<br>-------------------
<br><br><br>