Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Al-Shammari; Eiman Tamah Pages: 1 - 23 Abstract: This study introduces a novel hybrid model to enhance the prediction of benzene concentrations in three industrial regions in Kuwait, utilizing air quality data from 2022 to 2024. The hybrid model, developed through stacking techniques, integrates multiple ML algorithms to employ their collective strengths. The initial analysis involved examining pollutant trends and correlations among benzene, toluene, ethylbenzene, and xylenes (BTEX) compounds. We applied more than ten individual machine learning models to predict benzene levels. We then applied a hyperparameter, tuning the hybrid model to further enhance its prediction performance. By combining these models, the hybrid approach demonstrated superior predictive performance, evaluated using R-squared and mean squared error metrics. The results underscore the effectiveness of the hybrid model in providing accurate benzene concentration prediction, offering valuable insights for air quality management and pollution control in industrial regions. Keywords: Geographic Information Systems; Physical Sciences & Engineering; Geoinformatics Citation: International Journal of Applied Geospatial Research (IJAGR), Volume: 15, Issue: 1 (2024) Pages: 1-23 PubDate: 2024-01-01T05:00:00Z DOI: 10.4018/IJAGR.362003 Issue No:Vol. 15, No. 1 (2024)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Hamilton; Stuart E., Presotto, Andrea Pages: 1 - 16 Abstract: This manuscript presents a new global database that tracks annual global mangrove forest change rates since 2000. By synthesizing several remotely sensed databases such as Mangrove Forests of the World, Global Mangrove Watch, and High-Resolution Global Maps of 21st-Century Mangrove Forest Cover Change, this database provides mangrove forest change information at approximately 30 m annually and globally. It is a consistent and systematic mangrove forest change database across all years. Between 2000 and 2020, mangrove forests lost 3.42% of their original global area, shrinking from approximately 139,716 km2 in 2000 to 134,383 km2 in 2020, resulting in an annual loss rate of 0.17%. As of 2020, Indonesia, Brazil, Australia, Nigeria, and Malaysia are the top five mangrove-holding countries, containing slightly over 50% of the global mangrove holdings. Indonesia alone contains 22% of global mangrove forests. Keywords: Geographic Information Systems; Physical Sciences & Engineering; Geoinformatics Citation: International Journal of Applied Geospatial Research (IJAGR), Volume: 15, Issue: 1 (2024) Pages: 1-16 PubDate: 2024-01-01T05:00:00Z DOI: 10.4018/IJAGR.361727 Issue No:Vol. 15, No. 1 (2024)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Khademian; Mehrnaz, Bunch, Rick Pages: 1 - 23 Abstract: This article presents a sensitivity analysis of the main growing factors for wild American ginseng in North Carolina, USA. This study examines the influence and importance of ginseng's natural growing factors in the predictive models generated through the method of weighted linear combination by conducting a sensitivity analysis over the relative importance of growing factors. By identifying these factors, government agencies can more effectively plan law enforcement activities and streamline their preservation efforts to protect this valuable species. The results of our sensitivity analysis indicate that the shade-related factors and spatial factors play very important roles in predicting suitable areas for wild American ginseng to grow in nature in the context of North Carolina. This finding implies that the proper consideration of these factors substantially enhances model predictability and consistency of predictions with real-world observations. Keywords: Geographic Information Systems; Physical Sciences & Engineering; Geoinformatics Citation: International Journal of Applied Geospatial Research (IJAGR), Volume: 15, Issue: 1 (2024) Pages: 1-23 PubDate: 2024-01-01T05:00:00Z DOI: 10.4018/IJAGR.336927 Issue No:Vol. 15, No. 1 (2024)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Deka; Dhanjit, Das, Jyoti Prasad, Hazarika, Madine, Borah, Debashree Pages: 1 - 25 Abstract: Soil erosion is one of the most crucial land degradation problems and is considered the most critical environmental hazard worldwide. The present study uses remote sensing data integrated with the geographical information system (GIS) technique and the revised universal soil loss equation (RUSLE) model for assessing the annual average soil loss of the Digaru watershed of India for 1999 and 2020. The estimated mean gross yearly soil loss from the entire watershed was 102716 t yr-1 in 1999 and 178931.6 t yr-1 in 2020. The overall average soil loss rate increased significantly between 1999 and 2020, rising from 4.73 t—ha-1yr-1 to 8.43 t—ha-1yr-1. The sub-watersheds are prioritized as high (≥ 40 t ha−1yr−1), moderate (20–40 t ha−1yr−1), and low (<20 t ha−1yr−1) based on the spatial distribution of soil erosion. Seven sub-watersheds have been grouped under low priority, followed by seven under moderate priority and one under high priority. This study demands instant attention for soil and water conservation efforts in highly eroded watershed areas. Keywords: Geographic Information Systems; Physical Sciences & Engineering; Geoinformatics Citation: International Journal of Applied Geospatial Research (IJAGR), Volume: 15, Issue: 1 (2024) Pages: 1-25 PubDate: 2024-01-01T05:00:00Z DOI: 10.4018/IJAGR.340039 Issue No:Vol. 15, No. 1 (2024)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Boes; Kevin J., Hotalling, Danielle A., Taylor, Jack H., Guetterman, Timothy C., Dhitinut (DT) Ratnapradipa (e303ad63-919d-40c8-bfb0-76de4db29e7a Pages: 1 - 15 Abstract: Inland flooding poses significant acute and longer-term health risks, but many individuals living in or near floodplains may be unaware of their danger. Major flooding occurred in the Midwest USA during 2019. Our objective was to assess inland flood-related risk reduction behaviors and preparedness in flood-prone communities to inform risk communication and flood education interventions. We mailed a survey to residential addresses in the floodplains of Iowa and Nebraska in 2022 to assess flood knowledge, awareness, and risk reduction behaviors (such as having a flood plan). The 258 survey responses were linked to area-level Social Vulnerability Index (2020) and flood hazard maps to assess whether flood awareness and reduction behaviors were associated with risk. None of the examined factors explained flood-related behaviors well, although area-level race variables and distance from a major city were statistically significant (p<.05) for overall flood-related behavior. More targeted approaches may be warranted. Keywords: Geographic Information Systems; Physical Sciences & Engineering; Geoinformatics Citation: International Journal of Applied Geospatial Research (IJAGR), Volume: 15, Issue: 1 (2024) Pages: 1-15 PubDate: 2024-01-01T05:00:00Z DOI: 10.4018/IJAGR.351240 Issue No:Vol. 15, No. 1 (2024)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Shults; Daniel D., Nowlin, John W., Massey, Joseph H., Reba, Michele L. Pages: 1 - 22 Abstract: In eastern Arkansas, the use of surface water for crop irrigation is steadily increasing in response to declining aquifers. Effective conjunctive water management requires accurate and timely information on the locations, sizes, and numbers of on-farm irrigation reservoirs. A method for remotely locating and characterizing on-farm reservoirs was developed using relative elevation and near-infrared imagery. With 62% accuracy, the method automatically identified 429 irrigation reservoirs within a 1.9-Mha area in less than an hour using an off-the-shelf laptop. Reservoirs not accurately identified (i.e., false negatives) were caused by the presence of vegetation or turbidity within the reservoirs. There were no false positive detections. This approach for identifying elevated reservoirs is applicable across the Mississippi Alluvial Plain (MAP) that encompasses over 4-Mha of irrigated cropland and other agricultural areas having low-relief. Keywords: Geographic Information Systems; Physical Sciences & Engineering; Geoinformatics Citation: International Journal of Applied Geospatial Research (IJAGR), Volume: 15, Issue: 1 (2024) Pages: 1-22 PubDate: 2024-01-01T05:00:00Z DOI: 10.4018/IJAGR.337287 Issue No:Vol. 15, No. 1 (2024)
Hybrid journal (It can contain Open Access articles)
