Forest Fire Prediction Using Multi-Source Deep Learning

被引：2

作者：

Mutakabbir, Abdul ^{[1
]}

Lung, Chung-Horng ^{[1
]}

Ajila, Samuel A. ^{[1
]}

Zaman, Marzia ^{[2
]}

Naik, Kshirasagar ^{[3
]}

Purcell, Richard ^{[4
]}

Sampalli, Srinivas ^{[4
]}

机构：

[1] Carleton Univ, Dept Syst & Comp Engn, Ottawa, ON, Canada

[2] Cistel Technol, Res & Dev, Ottawa, ON, Canada

[3] Univ Waterloo, Dept Elect & Comp Engn, Waterloo, ON, Canada

[4] Dalhousie Univ, Fac Comp Sci, Halifax, NS, Canada

来源：

BIG DATA TECHNOLOGIES AND APPLICATIONS, EAI INTERNATIONAL CONFERENCE, BDTA 2023 | 2024年 / 555卷

基金：

加拿大自然科学与工程研究理事会;

关键词：

Deep Learning; Multi-Modal; Multi-Source Data; Big Data; Big Data Analysis; Binary Classification; Forest Fires;

D O I：

10.1007/978-3-031-52265-9_9

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Forest fire prediction is an important aspect of combating forest fires. This research focuses on the effectiveness of multi-source data (lightning, hydrometric and weather) in the probability prediction of forest fires using deep learning. The results showed that the weather model had the best predictive power (average F1Score = 0.955). The lightning model had an average F1Score = 0.924, while the hydrometric model had an average F1Score = 0.690. The single-source models were then merged to see the impact of the multi-source data. The multi-source model had an average F1Score = 0.929, whereas the average F1Score for the previous three single-source model was 0.856. The results showed that the multi-source model performed similarly to the best-performing single-source model (weather) with a 60% reduction in training data. The multi-source model had a negligible impact from the poor-performing single-source model (hydrometric).

引用

页码：135 / 146

页数：12

共 18 条

[1]

Akkus C, 2023, arXiv, DOI DOI 10.48550/ARXIV.2301.04856

[2]

Canada N.R., 2022, The State of Canada's Forests: Annual Report 2022

[3] A Survey on Deep Learning for Multimodal Data Fusion [J].

Gao, Jing ;

Li, Peng ;

Chen, Zhikui ;

Zhang, Jianing .

NEURAL COMPUTATION, 2020, 32 (05) :829-864

[4]

Holle RL, 2014, 2014 INTERNATIONAL CONFERENCE ON LIGHTNING PROTECTION (ICLP), P1390, DOI 10.1109/ICLP.2014.6973348

[5]

Johnson E. A., 2001, Forest Fires: Behavior and Ecological Effects

[6] Deep Learning and Data Sampling with Imbalanced Big Data [J].

Johnson, Justin M. ;

Khoshgoftaar, Taghi M. .

2019 IEEE 20TH INTERNATIONAL CONFERENCE ON INFORMATION REUSE AND INTEGRATION FOR DATA SCIENCE (IRI 2019), 2019, :175-183

[7] Cloud-to-Ground Lightning in Canada: 20 Years of CLDN Data [J].

Kochtubajda, Bohdan ;

Burrows, William R. .

ATMOSPHERE-OCEAN, 2020, 58 (05) :316-332

[8] RMDL: Random Multimodel Deep Learning for Classification [J].

Kowsari, Kamran ;

Heidarysafa, Mojtaba ;

Brown, Donald E. ;

Meimandi, Kiana Jafari ;

Barnes, Laura E. .

2ND INTERNATIONAL CONFERENCE ON INFORMATION SYSTEM AND DATA MINING (ICISDM 2018), 2018, :19-28

[9]

Mapari R.G., 2022, 2 INT C INTELLIGENT

[10] Spatio-Temporal Agnostic Deep Learning Modeling of Forest Fire Prediction Using Weather Data [J].

Mutakabbir, Abdul ;

Lung, Chung-Horng ;

Ajila, Samuel A. ;

Zaman, Marzia ;

Naik, Kshirasagar ;

Purcell, Richard ;

Sampalli, Srinivas .

2023 IEEE 47TH ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE, COMPSAC, 2023, :346-351

← 1 2 →