دورية أكاديمية
Global fire modelling and control attributions based on the ensemble machine learning and satellite observations
العنوان: | Global fire modelling and control attributions based on the ensemble machine learning and satellite observations |
---|---|
المؤلفون: | Yulong Zhang, Jiafu Mao, Daniel M. Ricciuto, Mingzhou Jin, Yan Yu, Xiaoying Shi, Stan Wullschleger, Rongyun Tang, Jicheng Liu |
المصدر: | Science of Remote Sensing, Vol 7, Iss , Pp 100088- (2023) |
بيانات النشر: | Elsevier, 2023. |
سنة النشر: | 2023 |
المجموعة: | LCC:Physical geography LCC:Science |
مصطلحات موضوعية: | Contemporary fire dynamics, Global fire modeling, Fire attributions, Ensemble machine learning, Remote sensing, Climate-vegetation-human controls, Physical geography, GB3-5030, Science |
الوصف: | Contemporary fire dynamics is one of the most complex and least understood land surface phenomena. Global fire controls related to climate, vegetation, and anthropogenic activity are usually intertwined, and difficult to disentangle in a quantitative way. Here, we leveraged an ensemble of five machine learning (ML) models and multiple satellite-based observations to conduct global fire modeling for three fire metrics (burned area, fire number, and fire size), and quantified driving mechanisms underlying annual fire changes in a spatially resolved manner for the period 2003–2019. Ensemble learning is a meta-approach that combines multiple ML predictions to improve accuracy, robustness, and generalization performance. We found that the optimized ensemble ML well reproduced annual dynamics of global burned area (R2 = 0.90, P |
نوع الوثيقة: | article |
وصف الملف: | electronic resource |
اللغة: | English |
تدمد: | 2666-0172 |
العلاقة: | http://www.sciencedirect.com/science/article/pii/S2666017223000135Test; https://doaj.org/toc/2666-0172Test |
DOI: | 10.1016/j.srs.2023.100088 |
الوصول الحر: | https://doaj.org/article/814e0b50a4ed4388941adfc1ce3b1de5Test |
رقم الانضمام: | edsdoj.814e0b50a4ed4388941adfc1ce3b1de5 |
قاعدة البيانات: | Directory of Open Access Journals |
تدمد: | 26660172 |
---|---|
DOI: | 10.1016/j.srs.2023.100088 |