: Floods are natural disasters that can damage lives, property, and the economy. Therefore, it is necessary to have a reliable and accurate flood forecasting system to provide early warning in time. Although several Mathematical models have been developed and used to forecast floods continuously for decades, most require up-to-date and specific physical data, including a high experience user, to provide and interpret the result. It is an obstacle for use in remote areas with incomplete information and a lack of specialists. This study, therefore, developed a real-time flood forecasting system with Machine Learning by applying a 2-variable sliding window technique to restructure the data, which can solve the problem of data limitation. Thung Song District Nakhon Si Thammarat Province was selected to test this newly developed model. By importing the water level data of two water level observed stations, SWR025 at the upstream and NKO001 at Thung Song Municipality, into five machine learning algorithms (Linear Regression, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Random Forest) for forecasting the water level every 30 minutes for the next 5 hours. Their performance was compared by the MSE, MAE, and R 2, which ranged from 0.006-0.013, 0.044-0.063, and 0.518-0.750, respectively. The Random Forest was the most efficient algorithm for the 3-hour forecast with an efficiency value of MSE 0.006, MAE 0.044, and R 2 0.75. The developed ML flood forecasting model was validated by the flood data in November 2021 and showed good agreement. Then, the extent of the inundation area was evaluated by the mathematical model. Next, the water depth and surface elevation were transformed and applied to GIS. Finally, the flood risk areas on Google Maps under that specific rainfall are promptly notified to the people three hours before the flood occurs.
{"title":"DEVELOPING A FLOOD FORECASTING SYSTEM WITH MACHINE LEARNING AND APPLYING TO GEOGRAPHIC INFORMATION SYSTEM","authors":"Jirayu Pungching, Sitang Pilailar","doi":"10.21163/gt_2023.181.01","DOIUrl":"https://doi.org/10.21163/gt_2023.181.01","url":null,"abstract":": Floods are natural disasters that can damage lives, property, and the economy. Therefore, it is necessary to have a reliable and accurate flood forecasting system to provide early warning in time. Although several Mathematical models have been developed and used to forecast floods continuously for decades, most require up-to-date and specific physical data, including a high experience user, to provide and interpret the result. It is an obstacle for use in remote areas with incomplete information and a lack of specialists. This study, therefore, developed a real-time flood forecasting system with Machine Learning by applying a 2-variable sliding window technique to restructure the data, which can solve the problem of data limitation. Thung Song District Nakhon Si Thammarat Province was selected to test this newly developed model. By importing the water level data of two water level observed stations, SWR025 at the upstream and NKO001 at Thung Song Municipality, into five machine learning algorithms (Linear Regression, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Random Forest) for forecasting the water level every 30 minutes for the next 5 hours. Their performance was compared by the MSE, MAE, and R 2, which ranged from 0.006-0.013, 0.044-0.063, and 0.518-0.750, respectively. The Random Forest was the most efficient algorithm for the 3-hour forecast with an efficiency value of MSE 0.006, MAE 0.044, and R 2 0.75. The developed ML flood forecasting model was validated by the flood data in November 2021 and showed good agreement. Then, the extent of the inundation area was evaluated by the mathematical model. Next, the water depth and surface elevation were transformed and applied to GIS. Finally, the flood risk areas on Google Maps under that specific rainfall are promptly notified to the people three hours before the flood occurs.","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49032599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"CATEGORIZING THE CAUSES OF OCCURRENCE OF CHATEAU BROWNFIELDS: A CASE STUDY ON THE CZECH REPUBLIC","authors":"Kamila Turečková","doi":"10.21163/gt_2022.172.18","DOIUrl":"https://doi.org/10.21163/gt_2022.172.18","url":null,"abstract":"","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42438849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MAPPING OF SUBAK AREA BOUNDARIES AND SOIL FERTILITY FOR AGRICULTURAL LAND CONSERVATION","authors":"Ida Bagus Putu Bhayunagiri, Moh Saifulloh","doi":"10.21163/gt_2022.172.17","DOIUrl":"https://doi.org/10.21163/gt_2022.172.17","url":null,"abstract":"","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46442148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A NEAR FUTURE CLIMATE CHANGE IMPACTS ON WATER RESOURCES IN THE UPPER CHAO PHRAYA RIVER BASIN IN THAILAND","authors":"N. Yoobanpot, Weerayuth Pratoomchai","doi":"10.21163/gt_2022.172.16","DOIUrl":"https://doi.org/10.21163/gt_2022.172.16","url":null,"abstract":"","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41464976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nayot Kulpanich, Morakot Worachairungreung, K. Waiyasusri, Pornperm Sae-ngow, Dusadee Pinasu
{"title":"HEIGHT MEASUREMENT AND OIL PALM YIELD PREDICTION USING UNMANNED AERIAL VEHICLE (UAV) DATA TO CREATE CANOPY HEIGHT MODEL (CHM)","authors":"Nayot Kulpanich, Morakot Worachairungreung, K. Waiyasusri, Pornperm Sae-ngow, Dusadee Pinasu","doi":"10.21163/gt_2022.172.14","DOIUrl":"https://doi.org/10.21163/gt_2022.172.14","url":null,"abstract":"","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43097979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"NIGHTTIME AND DAYTIME POPULATION ESTIMATION FROM OPEN DATA","authors":"Nelson Mileu, M. Queirós","doi":"10.21163/gt_2022.172.15","DOIUrl":"https://doi.org/10.21163/gt_2022.172.15","url":null,"abstract":"","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41431115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"DAILY STREAMFLOW FORECASTING USING EXTREME LEARNING MACHINE AND OPTIMIZATION ALGORITHM. CASE STUDY: TRA KHUC RIVER IN VIETNAM","authors":"H. Nguyen","doi":"10.21163/gt_2022.172.13","DOIUrl":"https://doi.org/10.21163/gt_2022.172.13","url":null,"abstract":"","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42652925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: The study develop of algorithms for the tropical mangrove chlorophyll-a, biomass and carbon based on the field data measurements at Cawan Island Sumatera Indonesia and Sentinel-2A satellite data. Samples of mangrove leaf were used for chlorophylla-a measurements using spectrometry method. Field sampling data using purposive sampling method. Data of mangrove tree diameter at breast height (DBH) was processed using allometric equation to estimate the mangrove biomass and carbon content. Algorithms were developed after performing a series of polynomial regressions of field and Sentinel-2A satellite data and then select the highest correlation coefficient. The dominant mangrove is Rhizophora apiculata . The field mangrove leaf chlorophyll-a content ranged from 14.03-15.77 mg.ml - 3 , while the estimated chlorophyll-a from algorithm is in the range of 13.714-16 mg.ml -3 . Calculated field mangrove biomass is in the range of 66.31-85.05 tons.ha -1 , while the value from algorithms is in the range of 51-90 tons.ha -1 . The highest biomass and carbon storage is in the trunks. This study produces the algorithm of mangrove leaf chlorophylll-a = 0.0002((B 4 + B 2 )/2) 2 – 0.057((B 4 + B 2 )/2) + 16.79, with RMSE of 0.072 mg.m -3 . Algorithm for mangrove biomass = 24.69(B 4 /Band 2 ) 2 - 47.41(B 4 /B 2 ) + 36.06, with RMSE of 0.337 tons/0.2ha and algorithm for mangrove carbon = 10.071(B 4 /B 2 ) 2 – 23.159(B 4 /B 2 ) + 44.233; with RMSE of 0.235 tonsC/0.2ha. The new insight in this study is that the algorithm developments can be applied for mangrove chlorophyll-a content, biomass and carbon content estimation using any optical satellite data based on its relevant spectral range. This algorithm development is an open approach method based on highest correlation coefficient on regression equation of the field and the satellite spectral value. The algorithms resulted from this study can be applied over wide and in any area in the tropics.
{"title":"ALGORITHMS DEVELOPMENT OF THE FIELD MANGROVE CHLOROPHYLL-a BIOMASS, CARBON BASED ON SENTINEL-2A DATA AT CAWAN ISLAND, SUMATERA, INDONESIA","authors":"Agus Hartoko, Aulia Rahim, N. Latifah","doi":"10.21163/gt_2022.172.11","DOIUrl":"https://doi.org/10.21163/gt_2022.172.11","url":null,"abstract":": The study develop of algorithms for the tropical mangrove chlorophyll-a, biomass and carbon based on the field data measurements at Cawan Island Sumatera Indonesia and Sentinel-2A satellite data. Samples of mangrove leaf were used for chlorophylla-a measurements using spectrometry method. Field sampling data using purposive sampling method. Data of mangrove tree diameter at breast height (DBH) was processed using allometric equation to estimate the mangrove biomass and carbon content. Algorithms were developed after performing a series of polynomial regressions of field and Sentinel-2A satellite data and then select the highest correlation coefficient. The dominant mangrove is Rhizophora apiculata . The field mangrove leaf chlorophyll-a content ranged from 14.03-15.77 mg.ml - 3 , while the estimated chlorophyll-a from algorithm is in the range of 13.714-16 mg.ml -3 . Calculated field mangrove biomass is in the range of 66.31-85.05 tons.ha -1 , while the value from algorithms is in the range of 51-90 tons.ha -1 . The highest biomass and carbon storage is in the trunks. This study produces the algorithm of mangrove leaf chlorophylll-a = 0.0002((B 4 + B 2 )/2) 2 – 0.057((B 4 + B 2 )/2) + 16.79, with RMSE of 0.072 mg.m -3 . Algorithm for mangrove biomass = 24.69(B 4 /Band 2 ) 2 - 47.41(B 4 /B 2 ) + 36.06, with RMSE of 0.337 tons/0.2ha and algorithm for mangrove carbon = 10.071(B 4 /B 2 ) 2 – 23.159(B 4 /B 2 ) + 44.233; with RMSE of 0.235 tonsC/0.2ha. The new insight in this study is that the algorithm developments can be applied for mangrove chlorophyll-a content, biomass and carbon content estimation using any optical satellite data based on its relevant spectral range. This algorithm development is an open approach method based on highest correlation coefficient on regression equation of the field and the satellite spectral value. The algorithms resulted from this study can be applied over wide and in any area in the tropics.","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45349147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Randy Ardianto, A. Ismanto, J. Sampurno, S. Widada
{"title":"TIDAL FLOOD MODEL PROJECTION USING LAND SUBSIDENCE PARAMETER IN PONTIANAK, INDONESIA","authors":"Randy Ardianto, A. Ismanto, J. Sampurno, S. Widada","doi":"10.21163/gt_2022.172.12","DOIUrl":"https://doi.org/10.21163/gt_2022.172.12","url":null,"abstract":"","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44653102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: El Niño Southern Oscillation (ENSO) and Indian Ocean Dipole (IOD) can affect the increase in rainfall intensity and the number of dry days, also known as dry spells that can cause drought and increase the potential for forest fires. This study examines the effect of ENSO and IOD conditions on the joint distribution of the number of dry days and total precipitation in a fire-prone area in southern Sumatra, Indonesia. The joint distribution is constructed using rotated copulas from several families, including Gaussian, student’s t, Clayton, Gumbel, Frank, Joe, Galambos, BB1, BB6, BB7, and BB8. Fire-prone areas are defined using k-mean clustering, while the copula parameters are estimated using the inference of function for margins (IFM) method. Based on the peak of joint probability density functions (PDFs), ENSO and IOD conditions had a significant effect in the dry season but had no significant effect in the rainy season. The peak of joint PDFs is getting to the dry-dry conditions when the ENSO and IOD indexes increase in the dry season. However, based on coincidence probability, ENSO conditions still influence the joint distribution between the number of dry days and total precipitation during the rainy season but not with IOD conditions. The lower the ENSO index, the higher the probability of wet conditions co-occurring in the number of dry days and total precipitation. Meanwhile, ENSO and IOD conditions significantly affect the coincidence probability between the number of dry days and total precipitation. Moderate-Strong El Niño has the most considerable coincidence probability of 68.5%, followed by Positive IOD with 62.6%. The two conditions had similar effects on the joint distribution of the number of dry days and total precipitation. Moreover, the association between the number of dry days and the total precipitation was stronger in the dry season than in the rainy
{"title":"JOINT DISTRIBUTION AND COINCIDENCE PROBABILITY OF THE NUMBER OF DRY DAYS AND THE TOTAL AMOUNT OF PRECIPITATION IN SOUTHERN SUMATRA FIRE-PRONE AREA","authors":"S. Nurdiati, M. Najib, Achmad Syarief Thalib","doi":"10.21163/gt_2022.172.10","DOIUrl":"https://doi.org/10.21163/gt_2022.172.10","url":null,"abstract":": El Niño Southern Oscillation (ENSO) and Indian Ocean Dipole (IOD) can affect the increase in rainfall intensity and the number of dry days, also known as dry spells that can cause drought and increase the potential for forest fires. This study examines the effect of ENSO and IOD conditions on the joint distribution of the number of dry days and total precipitation in a fire-prone area in southern Sumatra, Indonesia. The joint distribution is constructed using rotated copulas from several families, including Gaussian, student’s t, Clayton, Gumbel, Frank, Joe, Galambos, BB1, BB6, BB7, and BB8. Fire-prone areas are defined using k-mean clustering, while the copula parameters are estimated using the inference of function for margins (IFM) method. Based on the peak of joint probability density functions (PDFs), ENSO and IOD conditions had a significant effect in the dry season but had no significant effect in the rainy season. The peak of joint PDFs is getting to the dry-dry conditions when the ENSO and IOD indexes increase in the dry season. However, based on coincidence probability, ENSO conditions still influence the joint distribution between the number of dry days and total precipitation during the rainy season but not with IOD conditions. The lower the ENSO index, the higher the probability of wet conditions co-occurring in the number of dry days and total precipitation. Meanwhile, ENSO and IOD conditions significantly affect the coincidence probability between the number of dry days and total precipitation. Moderate-Strong El Niño has the most considerable coincidence probability of 68.5%, followed by Positive IOD with 62.6%. The two conditions had similar effects on the joint distribution of the number of dry days and total precipitation. Moreover, the association between the number of dry days and the total precipitation was stronger in the dry season than in the rainy","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":null,"pages":null},"PeriodicalIF":0.7,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44225543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：