Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke <i>Opisthorchis viverrini</i> (<i>OV</i>) Infection in Small Sub-Watersheds
Infection of liver flukes (<i>Opisthorchis viverrini</i>) is partly due to their suitability for habitats in sub-basin areas, which causes the intermediate host to remain in the watershed system in all seasons. The spatial monitoring of fluke at the small basin scale is important because...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/12/12/503 |
| _version_ | 1827574615163011072 |
|---|---|
| author | Benjamabhorn Pumhirunroj Patiwat Littidej Thidarut Boonmars Kanokwan Bootyothee Atchara Artchayasawat Phusit Khamphilung Donald Slack |
| author_facet | Benjamabhorn Pumhirunroj Patiwat Littidej Thidarut Boonmars Kanokwan Bootyothee Atchara Artchayasawat Phusit Khamphilung Donald Slack |
| author_sort | Benjamabhorn Pumhirunroj |
| collection | DOAJ |
| description | Infection of liver flukes (<i>Opisthorchis viverrini</i>) is partly due to their suitability for habitats in sub-basin areas, which causes the intermediate host to remain in the watershed system in all seasons. The spatial monitoring of fluke at the small basin scale is important because this can enable analysis at the level of the factors involved that influence infections. A spatial mathematical model was weighted by the nine spatial factors <i>X</i><sub>1</sub> (index of land-use types), <i>X</i><sub>2</sub> (index of soil drainage properties), <i>X</i><sub>3</sub> (distance index from the road network, <i>X</i><sub>4</sub> (distance index from surface water resources), <i>X</i><sub>5</sub> (distance index from the flow accumulation lines), <i>X</i><sub>6</sub> (index of average surface temperature), <i>X</i><sub>7</sub> (average surface moisture index), <i>X</i><sub>8</sub> (average normalized difference vegetation index), and <i>X</i><sub>9</sub> (average soil-adjusted vegetation index) by dividing the analysis into two steps: (1) the sub-basin boundary level was analyzed with an ordinary least square (OLS) model used to select the spatial criteria of liver flukes aimed at analyzing the factors related to human liver fluke infection according to sub-watersheds, and (2) we used the infection risk positional analysis level through machine-learning-based forest classification and regression (FCR) to display the predictive results of infection risk locations along stream lines. The analysis results show four prototype models that import different independent variable factors. The results show that Model 1 and Model 2 gave the most AUC (0.964), and the variables that influenced infection risk the most were the distance to stream lines and the distance to water bodies; the NDMI and NDVI factors rarely affected the accuracy. This FCR machine-learning application approach can be applied to the analysis of infection risk areas at the sub-basin level, but independent variables must be screened with a preliminary mathematical model weighted to the spatial units in order to obtain the most accurate predictions. |
| first_indexed | 2024-03-08T20:42:35Z |
| format | Article |
| id | doaj.art-395682ad369640ab81e62041959c6644 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-08T20:42:35Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-395682ad369640ab81e62041959c66442023-12-22T14:13:17ZengMDPI AGISPRS International Journal of Geo-Information2220-99642023-12-01121250310.3390/ijgi12120503Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke <i>Opisthorchis viverrini</i> (<i>OV</i>) Infection in Small Sub-WatershedsBenjamabhorn Pumhirunroj0Patiwat Littidej1Thidarut Boonmars2Kanokwan Bootyothee3Atchara Artchayasawat4Phusit Khamphilung5Donald Slack6Program in Animal Science, Faculty of Agricultural Technology, Sakon Nakhon Rajabhat University, Sakon Nakhon 47000, ThailandGeoinformatics Research Unit for Spatial Management, Department of Geoinformatics, Faculty of Informatics, Mahasarakham University, Maha Sarakham 44150, ThailandDepartment of Parasitology, Faculty of Medicine, Khon Kaen University, Khon Kaen 40002, ThailandProgram in Animal Science, Faculty of Agricultural Technology, Sakon Nakhon Rajabhat University, Sakon Nakhon 47000, ThailandDepartment of Parasitology, Faculty of Medicine, Khon Kaen University, Khon Kaen 40002, ThailandGeoinformatics Research Unit for Spatial Management, Department of Geoinformatics, Faculty of Informatics, Mahasarakham University, Maha Sarakham 44150, ThailandDepartment of Civil & Architectural Engineering & Mechanics, University of Arizona, 1209 E. Second St., P.O. Box 210072, Tucson, AZ 85721, USAInfection of liver flukes (<i>Opisthorchis viverrini</i>) is partly due to their suitability for habitats in sub-basin areas, which causes the intermediate host to remain in the watershed system in all seasons. The spatial monitoring of fluke at the small basin scale is important because this can enable analysis at the level of the factors involved that influence infections. A spatial mathematical model was weighted by the nine spatial factors <i>X</i><sub>1</sub> (index of land-use types), <i>X</i><sub>2</sub> (index of soil drainage properties), <i>X</i><sub>3</sub> (distance index from the road network, <i>X</i><sub>4</sub> (distance index from surface water resources), <i>X</i><sub>5</sub> (distance index from the flow accumulation lines), <i>X</i><sub>6</sub> (index of average surface temperature), <i>X</i><sub>7</sub> (average surface moisture index), <i>X</i><sub>8</sub> (average normalized difference vegetation index), and <i>X</i><sub>9</sub> (average soil-adjusted vegetation index) by dividing the analysis into two steps: (1) the sub-basin boundary level was analyzed with an ordinary least square (OLS) model used to select the spatial criteria of liver flukes aimed at analyzing the factors related to human liver fluke infection according to sub-watersheds, and (2) we used the infection risk positional analysis level through machine-learning-based forest classification and regression (FCR) to display the predictive results of infection risk locations along stream lines. The analysis results show four prototype models that import different independent variable factors. The results show that Model 1 and Model 2 gave the most AUC (0.964), and the variables that influenced infection risk the most were the distance to stream lines and the distance to water bodies; the NDMI and NDVI factors rarely affected the accuracy. This FCR machine-learning application approach can be applied to the analysis of infection risk areas at the sub-basin level, but independent variables must be screened with a preliminary mathematical model weighted to the spatial units in order to obtain the most accurate predictions.https://www.mdpi.com/2220-9964/12/12/503<i>Opisthorchis viverrini</i>forest-based classification and regressionmachine learningordinary least square |
| spellingShingle | Benjamabhorn Pumhirunroj Patiwat Littidej Thidarut Boonmars Kanokwan Bootyothee Atchara Artchayasawat Phusit Khamphilung Donald Slack Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke <i>Opisthorchis viverrini</i> (<i>OV</i>) Infection in Small Sub-Watersheds ISPRS International Journal of Geo-Information <i>Opisthorchis viverrini</i> forest-based classification and regression machine learning ordinary least square |
| title | Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke <i>Opisthorchis viverrini</i> (<i>OV</i>) Infection in Small Sub-Watersheds |
| title_full | Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke <i>Opisthorchis viverrini</i> (<i>OV</i>) Infection in Small Sub-Watersheds |
| title_fullStr | Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke <i>Opisthorchis viverrini</i> (<i>OV</i>) Infection in Small Sub-Watersheds |
| title_full_unstemmed | Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke <i>Opisthorchis viverrini</i> (<i>OV</i>) Infection in Small Sub-Watersheds |
| title_short | Machine-Learning-Based Forest Classification and Regression (FCR) for Spatial Prediction of Liver Fluke <i>Opisthorchis viverrini</i> (<i>OV</i>) Infection in Small Sub-Watersheds |
| title_sort | machine learning based forest classification and regression fcr for spatial prediction of liver fluke i opisthorchis viverrini i i ov i infection in small sub watersheds |
| topic | <i>Opisthorchis viverrini</i> forest-based classification and regression machine learning ordinary least square |
| url | https://www.mdpi.com/2220-9964/12/12/503 |
| work_keys_str_mv | AT benjamabhornpumhirunroj machinelearningbasedforestclassificationandregressionfcrforspatialpredictionofliverflukeiopisthorchisviverriniiioviinfectioninsmallsubwatersheds AT patiwatlittidej machinelearningbasedforestclassificationandregressionfcrforspatialpredictionofliverflukeiopisthorchisviverriniiioviinfectioninsmallsubwatersheds AT thidarutboonmars machinelearningbasedforestclassificationandregressionfcrforspatialpredictionofliverflukeiopisthorchisviverriniiioviinfectioninsmallsubwatersheds AT kanokwanbootyothee machinelearningbasedforestclassificationandregressionfcrforspatialpredictionofliverflukeiopisthorchisviverriniiioviinfectioninsmallsubwatersheds AT atcharaartchayasawat machinelearningbasedforestclassificationandregressionfcrforspatialpredictionofliverflukeiopisthorchisviverriniiioviinfectioninsmallsubwatersheds AT phusitkhamphilung machinelearningbasedforestclassificationandregressionfcrforspatialpredictionofliverflukeiopisthorchisviverriniiioviinfectioninsmallsubwatersheds AT donaldslack machinelearningbasedforestclassificationandregressionfcrforspatialpredictionofliverflukeiopisthorchisviverriniiioviinfectioninsmallsubwatersheds |