PreprintArticleVersion 1Preserved in Portico This version is not peer-reviewed
Building Models for Agricultural Land Fire Prediction Using Remote Sensed Environmental Data: A Case Study in Dien Bien Province, Vietnam (2003 – 2016)
Version 1
: Received: 21 July 2020 / Approved: 23 July 2020 / Online: 23 July 2020 (08:00:53 CEST)
How to cite:
Nguyen, T.T.; Tran, T.D.; Linh, T.V.K.; Le, T.S.; Pham, T.T.; Ho, D.P. Building Models for Agricultural Land Fire Prediction Using Remote Sensed Environmental Data: A Case Study in Dien Bien Province, Vietnam (2003 – 2016). Preprints2020, 2020070535. https://doi.org/10.20944/preprints202007.0535.v1
Nguyen, T.T.; Tran, T.D.; Linh, T.V.K.; Le, T.S.; Pham, T.T.; Ho, D.P. Building Models for Agricultural Land Fire Prediction Using Remote Sensed Environmental Data: A Case Study in Dien Bien Province, Vietnam (2003 – 2016). Preprints 2020, 2020070535. https://doi.org/10.20944/preprints202007.0535.v1
Nguyen, T.T.; Tran, T.D.; Linh, T.V.K.; Le, T.S.; Pham, T.T.; Ho, D.P. Building Models for Agricultural Land Fire Prediction Using Remote Sensed Environmental Data: A Case Study in Dien Bien Province, Vietnam (2003 – 2016). Preprints2020, 2020070535. https://doi.org/10.20944/preprints202007.0535.v1
APA Style
Nguyen, T.T., Tran, T.D., Linh, T.V.K., Le, T.S., Pham, T.T., & Ho, D.P. (2020). Building Models for Agricultural Land Fire Prediction Using Remote Sensed Environmental Data: A Case Study in Dien Bien Province, Vietnam (2003 – 2016). Preprints. https://doi.org/10.20944/preprints202007.0535.v1
Chicago/Turabian Style
Nguyen, T.T., Trang Thanh Pham and Dang Phuc Ho. 2020 "Building Models for Agricultural Land Fire Prediction Using Remote Sensed Environmental Data: A Case Study in Dien Bien Province, Vietnam (2003 – 2016)" Preprints. https://doi.org/10.20944/preprints202007.0535.v1
Abstract
Agricultural land fires have been linked to various and adverse impacts on ecosystems, food security and the agriculture sector. Understanding the patterns and drivers of agricultural land fires is essential for effective agricultural land fire management. The key objectives of this study were to (1) analyze the temporal and spatial patterns of agricultural land fires using satellite remote sensed data, (2) assess a range of environmental conditions that could drive the occurrence of agricultural land fires, (3) determine the best model for predicting agricultural land fires and (4) determine the relative contribution of each environmental condition variable on the best predictive model. We used both univariate and multivariate regressions for the fire prediction capability of four independent environmental conditions (fuel, weather, topographic and anthropogenic). Analysis of historical satellite data revealed that agricultural land fires were more frequent than forested land fires. Our analyses also revealed that fuel condition was the most important variable for predicting agricultural land fires followed by weather, topographic and anthropogenic conditions. This study provides a novel multivariate model for predicting agricultural land fires that harbors the potential to improve agricultural land fire management and reduce fire risk within the agricultural sector.
Keywords
agricultural land; remote sensing; agricultural fire; fire predicting model
Subject
Biology and Life Sciences, Agricultural Science and Agronomy
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
,
,
,
