{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T05:18:55Z","timestamp":1762233535977,"version":"build-2065373602"},"reference-count":52,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["32101411"],"award-info":[{"award-number":["32101411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Specialized Research and Development Program of Henan Province","award":["252102210172"],"award-info":[{"award-number":["252102210172"]}]},{"name":"National Innovation Training Program of University Student","award":["202410475106"],"award-info":[{"award-number":["202410475106"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Wildfire risk assessment requires integrating heterogeneous geospatial data to capture complex environmental dynamics. This study develops a hierarchical multimodal fusion framework combining high-resolution aerial imagery, historical fire data, topography, meteorology, and vegetation indices within Google Earth Engine. We introduce three progressive fusion levels: a single-modality baseline (NAIP-WHP), fixed-weight fusion (FIXED), and a novel geographically adaptive dynamic-weight approach (FUSED) that adjusts feature contributions based on regional characteristics like human activity intensity or aridity. Machine learning benchmarking across 49 U.S. regions reveals that Support Vector Machines (SVM) applied to the FUSED dataset achieve optimal performance, with an AUC-ROC of 92.1%, accuracy of 83.3%, and inference speed of 1.238 milliseconds per sample. This significantly outperforms the fixed-weight fusion approach, which achieved an AUC-ROC of 78.2%, and the single-modality baseline, which achieved 73.8%, representing relative improvements of 17.8% and 24.8%, respectively. The 10 m resolution risk heatmaps demonstrate operational viability, achieving an 86.27% hit rate in Carlsbad Caverns, NM. SHAP-based interpretability analysis reveals terrain dominance and context-dependent vegetation effects, aligning with wildfire ecology principles.<\/jats:p>","DOI":"10.3390\/ijgi14110426","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T16:18:42Z","timestamp":1762186722000},"page":"426","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FireRisk-Multi: A Dynamic Multimodal Fusion Framework for High-Precision Wildfire Risk Assessment"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9388-5690","authenticated-orcid":false,"given":"Ke","family":"Yuan","sequence":"first","affiliation":[{"name":"School of Computer and Information Engineering, Henan University, Kaifeng 475001, China"},{"name":"Henan Spatial Information Processing Engineering Research Center, Henan University, Kaifeng 475001, China"}]},{"given":"Zhiruo","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Henan University, Kaifeng 475001, China"}]},{"given":"Yutong","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Henan University, Kaifeng 475001, China"}]},{"given":"Jing","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Henan University, Kaifeng 475001, China"}]},{"given":"Chunhui","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Henan University, Kaifeng 475001, China"}]},{"given":"Qian","family":"Tang","sequence":"additional","affiliation":[{"name":"Faculty of Geographical Science and Engineering, College of Geographical Sciences, Henan University, Zhengzhou 450046, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"11770","DOI":"10.1073\/pnas.1607171113","article-title":"Impact of anthropogenic climate change on wildfire across western US forests","volume":"113","author":"Abatzoglou","year":"2016","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"6764","DOI":"10.1038\/s41467-024-51154-7","article-title":"Drivers and impacts of the record-breaking 2023 wildfire season in Canada","volume":"15","author":"Jain","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1420","DOI":"10.1038\/s41559-024-02452-2","article-title":"Increasing frequency and intensity of the most extreme wildfires on Earth","volume":"8","author":"Cunningham","year":"2024","journal-title":"Nat. Ecol. Evol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1186","DOI":"10.1038\/s41558-024-02140-w","article-title":"Global burned area increasingly explained by climate change","volume":"14","author":"Burton","year":"2024","journal-title":"Nat. Clim. Change"},{"key":"ref_5","first-page":"21","article-title":"Australian fire weather as represented by the McArthur Forest Fire Danger Index and the Canadian Forest Fire Weather Index","volume":"53","author":"Dowdy","year":"2019","journal-title":"Clim. Dyn."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shen, S., Seneviratne, S.I., Wanyan, X., and Kirley, M. (2023). FireRisk: A remote sensing dataset for fire risk assessment with benchmarks using supervised and self-supervised learning. arXiv.","DOI":"10.1109\/DICTA60407.2023.00034"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kalantar, B., Ueda, N., Idrees, M.O., Janizadeh, S., Ahmadi, K., and Shabani, F. (2020). Forest fire susceptibility prediction based on machine learning models with resampling algorithms on remote sensing data. Remote Sens., 12.","DOI":"10.3390\/rs12223682"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1071\/WF20077","article-title":"Integrating remotely sensed fuel variables into wildfire danger assessment for China","volume":"30","author":"Quan","year":"2021","journal-title":"Int. J. Wildland Fire"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e01485","DOI":"10.1002\/ecm.1485","article-title":"The magnitude, direction, and tempo of forest change in Greater Yellowstone in a warmer world with more fire","volume":"92","author":"Turner","year":"2022","journal-title":"Ecol. Monogr."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1946","DOI":"10.1016\/j.agrformet.2009.06.022","article-title":"Assessment of forest fire seasonality using MODIS fire potential: A time series approach","volume":"149","author":"Huesca","year":"2009","journal-title":"Agric. For. Meteorol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"737","DOI":"10.14358\/PERS.83.10.737","article-title":"Land cover classification and feature extraction from National Agriculture Imagery Program (NAIP) orthoimagery: A review","volume":"83","author":"Maxwell","year":"2017","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"RG2004","DOI":"10.1029\/2005RG000183","article-title":"The shuttle radar topography mission","volume":"45","author":"Farr","year":"2007","journal-title":"Rev. Geophys."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1999","DOI":"10.1002\/qj.3803","article-title":"The ERA5 global reanalysis","volume":"146","author":"Hersbach","year":"2020","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_14","unstructured":"Didan, K., Miura, T., Solano, R., and Huete, A.R. (2025, February 17). MODIS Vegetation Index User\u2019s Guide, Available online: https:\/\/modis.gsfc.nasa.gov\/data\/dataprod\/mod13.php."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3881","DOI":"10.1080\/01431160600784234","article-title":"Predicting slow-drying fire weather index fuel moisture codes with NOAA-AVHRR images in Canada\u2019s northern boreal forests","volume":"27","author":"Oldford","year":"2006","journal-title":"Int. J. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1139\/x11-162","article-title":"Examining the utility of the Canadian Forest Fire Weather Index System in boreal peatlands","volume":"42","author":"Waddington","year":"2012","journal-title":"Can. J. For. Res."},{"key":"ref_17","first-page":"127","article-title":"Integrating Satellite-Derived Indices and Support Vector Machines for Enhanced Wildfire Detection: An Empirical Study on Australian Forest Fires","volume":"3","author":"Shahid","year":"2025","journal-title":"Front. Comput. Spat. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Papakis, I., Linardos, V., and Drakaki, M. (2025). A Multimodal Ensemble Deep Learning Model for Wildfire Prediction in Greece Using Satellite Imagery and Multi-Source Remote Sensing Data. Remote Sens., 17.","DOI":"10.3390\/rs17193310"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/JSTARS.2022.3219816","article-title":"CNN, RNN, or ViT? An evaluation of different deep learning architectures for spatio-temporal representation of sentinel time series","volume":"16","author":"Zhao","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"106152","DOI":"10.1016\/j.engappai.2023.106152","article-title":"Combining 2D encoding and convolutional neural network to enhance land cover mapping from Satellite Image Time Series","volume":"122","author":"Abidi","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Alipour, M., La Puma, I., Picotte, J., Shamsaei, K., Rowell, E., Watts, A., Kosovic, B., Ebrahimian, H., and Taciroglu, E. (2023). A multimodal data fusion and deep learning framework for large-scale wildfire surface fuel mapping. Fire, 6.","DOI":"10.3390\/fire6020036"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yang, J., Jiang, H., Wang, S., and Ma, X. (2024). A multi-scale deep learning algorithm for enhanced forest fire danger prediction using remote sensing images. Forests, 15.","DOI":"10.3390\/f15091581"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.rse.2017.06.031","article-title":"Google Earth Engine: Planetary-scale geospatial analysis for everyone","volume":"202","author":"Gorelick","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_24","unstructured":"Giglio, L., and Justice, C. (2024, June 15). MOD14A1 MODIS\/Terra Thermal Anomalies\/Fire Daily L3 Global 1km SIN Grid V006. NASA EOSDIS Land Processes DAAC 2015, Available online: https:\/\/lpdaac.usgs.gov\/products\/mod14a1v006\/."},{"key":"ref_25","unstructured":"Didan, K., and Barreto, A. (2024, June 15). VIIRS\/NPP Vegetation Indices 16-Day L3 Global 500m SIN Grid V001. NASA EOSDIS Land Processes DAAC 2018, Available online: https:\/\/lpdaac.usgs.gov\/products\/vnp13a1v001\/."},{"key":"ref_26","unstructured":"Schroeder, W., Oliva, P., Giglio, L., Quayle, B., Lorenz, E., and Morelli, F. (2022). VIIRS active fire products: Algorithm improvements and global validation. Remote Sens., 14."},{"key":"ref_27","unstructured":"[NASA] National Aeronautics and Space Administration, Land Processes Distributed Active Archive Center (2024, June 15). MOD\/MYD C6.1 MCD64A1 Burned Area Product, Available online: https:\/\/lpdaac.usgs.gov\/products\/mcd64a1v006\/."},{"key":"ref_28","unstructured":"(2024, November 05). SpatialReference.org. EPSG:32611 WGS 84\/UTM Zone 11N. Available online: https:\/\/spatialreference.org\/ref\/epsg\/32611\/."},{"key":"ref_29","unstructured":"[USDA] U.S. Department of Agriculture, Forest Service (2024, May 23). Wildfire Potential Hazard (WHP) 2023 Classification. ArcGIS Online. Available online: https:\/\/usfs.maps.arcgis.com\/home."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3314","DOI":"10.1073\/pnas.1718850115","article-title":"Rapid growth of the US wildland-urban interface raises wildfire risk","volume":"115","author":"Radeloff","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_31","unstructured":"Tsai, Y.H.H., Liang, P.P., Zadeh, A., Morency, L.P., and Salakhutdinov, R. (2018). Learning Factorized Multimodal Representations. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Singh, S., Saber, E., Markopoulos, P.P., and Heard, J. (2024). Regulating Modality Utilization within Multimodal Fusion Networks. Sensors, 24.","DOI":"10.3390\/s24186054"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1109\/JSTARS.2018.2794888","article-title":"A Multiscale and Multidepth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening","volume":"11","author":"Yuan","year":"2018","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_34","first-page":"117697","article-title":"Impacts of mining on vegetation phenology and sensitivity assessment of spectral vegetation indices to mining activities in arid\/semi-arid areas","volume":"337","author":"Sun","year":"2023","journal-title":"J. Environ. Manag."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.rse.2014.05.009","article-title":"A new soil roughness parameter for the modeling of radar backscattering over bare soil","volume":"152","author":"Zribi","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Bousbih, S., Zribi, M., El Hajj, M., Baghdadi, N., and Lili-Chabaane, Z. (2018). Soil moisture and irrigation mapping in a semi-arid region, based on the synergetic use of Sentinel-1 and Sentinel-2 data. Remote Sens., 10.","DOI":"10.3390\/rs10121953"},{"key":"ref_37","unstructured":"Dvo\u0159\u00e1kov\u00e1, M., Nov\u00e1k, V., and Zribi, M. (2021, January 11\u201316). Mapping of surface soil parameters (roughness, moisture and texture) using one radar X-band SAR configuration over bare agricultural semi-arid region. Proceedings of the IGARSS 2021, Brussels, Belgium."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wang, Q. (2022, January 24\u201326). Support Vector Machine Algorithm in Machine Learning. Proceedings of the 2022 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA), Dalian, China.","DOI":"10.1109\/ICAICA54878.2022.9844516"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_41","first-page":"3146","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"ref_42","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8\u201314). PyTorch: An imperative style, high-performance deep learning library. Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_43","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"ref_44","first-page":"113482","article-title":"A transformer-based fusion framework for wildfire risk assessment using heterogeneous geospatial data","volume":"287","author":"Li","year":"2023","journal-title":"Remote Sens. Environ."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_46","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume":"97","author":"Tan","year":"2019","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_47","first-page":"10096","article-title":"EfficientNetV2, Smaller models and faster training","volume":"139","author":"Tan","year":"2021","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_48","unstructured":"[IPCC] Intergovernmental Panel on Climate Change (2023). Climate Change 2023: Synthesis Report, Cambridge University Press."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"2390","DOI":"10.1002\/eap.1395","article-title":"Quantifying the human influence on fire ignition across the western USA","volume":"26","author":"Fusco","year":"2016","journal-title":"Ecol. Appl."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"2229","DOI":"10.1007\/s10980-019-00906-8","article-title":"The historical use of fire as a land management tool in New Zealand and the challenges for its continued use","volume":"34","author":"Baillie","year":"2019","journal-title":"Landsc. Ecol."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"135592","DOI":"10.1016\/j.scitotenv.2019.135592","article-title":"Wildfires in the wildland-urban interface: Key concepts and evaluation methodologies","volume":"707","author":"Vieira","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Szpakowski, D.M., and Jensen, J.L.R. (2019). A review of the applications of remote sensing in fire ecology. Remote Sens., 11.","DOI":"10.3390\/rs11222638"}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/11\/426\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T05:16:05Z","timestamp":1762233365000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/14\/11\/426"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,31]]},"references-count":52,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["ijgi14110426"],"URL":"https:\/\/doi.org\/10.3390\/ijgi14110426","relation":{},"ISSN":["2220-9964"],"issn-type":[{"type":"electronic","value":"2220-9964"}],"subject":[],"published":{"date-parts":[[2025,10,31]]}}}