Improved Wildfire Spread Prediction with Time-Series Data and the WSTS+ Benchmark
This work addresses wildfire prediction for environmental and safety applications, but it is incremental as it builds on prior methods and benchmarks.
The authors tackled wildfire spread prediction by evaluating existing data-driven models under controlled conditions, achieving state-of-the-art accuracy on the WSTS benchmark, and introduced the WSTS+ benchmark with doubled historical data and expanded geographic scope.
Recent research has demonstrated the potential of deep neural networks (DNNs) to accurately predict wildfire spread on a given day based upon high-dimensional explanatory data from a single preceding day, or from a time series of T preceding days. For the first time, we investigate a large number of existing data-driven wildfire modeling strategies under controlled conditions, revealing the best modeling strategies and resulting in models that achieve state-of-the-art (SOTA) accuracy for both single-day and multi-day input scenarios, as evaluated on a large public benchmark for next-day wildfire spread, termed the WildfireSpreadTS (WSTS) benchmark. Consistent with prior work, we found that models using time-series input obtained the best overall accuracy, suggesting this is an important future area of research. Furthermore, we create a new benchmark, WSTS+, by incorporating four additional years of historical wildfire data into the WSTS benchmark. Our benchmark doubles the number of unique years of historical data, expands its geographic scope, and, to our knowledge, represents the largest public benchmark for time-series-based wildfire spread prediction.