A Multi-Criteria Forest Fire Danger Assessment System on GIS Using Literature-Based Model and Analytical Hierarchy Process Model for Mediterranean Coast of Manavgat, Türkiye DOI Open Access
İzzet Ersoy, Emre Ünsal, Önder Gürsoy

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(5), P. 1971 - 1971

Published: Feb. 25, 2025

Forest fires pose significant environmental and economic risks, particularly in fire-prone regions like the Mediterranean coast of Türkiye. This study presents a comprehensive Fire Danger Assessment System (FoFiDAS), by integrating Geographic Information Systems (GIS), literature-based model, Analytical Hierarchy Process (AHP), machine learning (ML) to improve forest fire danger classification. Both models integrate 13 key parameters identified through literature. A comparison these revealed 53% overlap classifications. While AHP based on expert-weighted assessment, provided more structured localized classification, model relied broader scientific data but lacked adaptability. Pearson correlation analysis demonstrated strong between classifications historical occurrences, with scores 0.927 (AHP) 0.939 (literature-based). Further ROC confirmed predictive performance both models, yielding AUC values 0.91 0.9121 for respectively. Five ML algorithms were used validate classification performances, Artificial Neural Network (ANN) achieving highest accuracy (86.5%). The ANN algorithm exceeded 0.93 each class, F1-Score was above 0.85. FoFiDAS offers reliable tool supporting early intervention decision making.

Language: Английский

Research on Intelligent Information Processing and Decision Support Methods in Modern Agricultural and Forestry Economic Management DOI Open Access
Xingang Wang

Applied Mathematics and Nonlinear Sciences, Journal Year: 2025, Volume and Issue: 10(1)

Published: Jan. 1, 2025

Abstract With the rapid development of information technology, modern agroforestry economic management is gradually integrating intelligent processing and decision support system to improve efficiency quality making. In this study, a for economy developed, which uses convolutional neural networks an improved coordinated attention mechanism module (MA) as method. The algorithms such fuzzy hierarchical analysis entropy weight method are integrated make comprehensive judgment on decisions related agroforestry. in paper has reasoning accuracy 100% fostering 98.47% For projects, results calculated by consistent with given experts. technology selected 99.62% predicting yield agricultural forestry cash crop specific area. can optimize planting area crops higher benefits. conclusion, using decision-making promote sustainable economy.

Language: Английский

Citations

0

Research on the Optimization of National Governance System Based on Data Science under the Perspective of Marxism DOI Open Access
Lijun Tang

Applied Mathematics and Nonlinear Sciences, Journal Year: 2025, Volume and Issue: 10(1)

Published: Jan. 1, 2025

Abstract Data science can promote the intelligence of national governance methods, and enhance efficiency effectiveness through incorporation big data collection processing intelligent decision-making system. This paper systematically utilizes a variety methods to study analyze optimization strategy system under Marxist perspective. It evaluates effect digital transformation implemented in place A by constructing evaluation index system, provides focus indicators process using fuzzy hierarchical analysis. The average coefficient variation squared for Digital infrastructure, Agricultural digitization, Governance digitization is 0.734, 0.876, 0.775, respectively, which better discriminatory ability. Experts showed different emphasis on indicators, with “Product network sales rate” scoring lowest at 78.282. After implementing strategy, ecological level Site has been increasing year year. And based gets consistent satisfaction from residents, comprehensive rating about 4.26. theoretical support empirical enlightenment new era.

Language: Английский

Citations

0

A Multi-Criteria Forest Fire Danger Assessment System on GIS Using Literature-Based Model and Analytical Hierarchy Process Model for Mediterranean Coast of Manavgat, Türkiye DOI Open Access
İzzet Ersoy, Emre Ünsal, Önder Gürsoy

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(5), P. 1971 - 1971

Published: Feb. 25, 2025

Forest fires pose significant environmental and economic risks, particularly in fire-prone regions like the Mediterranean coast of Türkiye. This study presents a comprehensive Fire Danger Assessment System (FoFiDAS), by integrating Geographic Information Systems (GIS), literature-based model, Analytical Hierarchy Process (AHP), machine learning (ML) to improve forest fire danger classification. Both models integrate 13 key parameters identified through literature. A comparison these revealed 53% overlap classifications. While AHP based on expert-weighted assessment, provided more structured localized classification, model relied broader scientific data but lacked adaptability. Pearson correlation analysis demonstrated strong between classifications historical occurrences, with scores 0.927 (AHP) 0.939 (literature-based). Further ROC confirmed predictive performance both models, yielding AUC values 0.91 0.9121 for respectively. Five ML algorithms were used validate classification performances, Artificial Neural Network (ANN) achieving highest accuracy (86.5%). The ANN algorithm exceeded 0.93 each class, F1-Score was above 0.85. FoFiDAS offers reliable tool supporting early intervention decision making.

Language: Английский

Citations

0