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. Code, model weights, and data can be found at this repo.

Evapotranspiration (ET) is a key link between the global carbon, water and energy cycles. ET generally occurs from soil, vegetation and intercepted precipitation. ET components are commonly estimated using a combination of variables, including meteorology, vegetation, and soil moisture conditions. Although vegetation transpiration has a major effect on global ET variations, soil evaporation can also contribute significant water loss to the atmosphere. This study utilizes satellite derived soil moisture data from the NASA SMAP mission to produce global ET estimates using a modified Penman Monteith algorithm. The global ET results were assessed using other available ET benchmarks. In addition, the ET estimates were evaluated for monitoring spring onset in relation to other complementary satellite observations of vegetation phenology and landscape freeze/thaw metrics. The comparisons between global ET products showed similar latitudinal variation, but with larger differences in tropical rainforests. The spring onset results showed landscape thawing related to rising temperature facilitating the new release of plant-available soil moisture that accompanies a dramatic seasonal rise in both vegetation photosynthesis and ET.

This paper introduces an algorithm for determining data clusters called TILO/PRC (Topologically Intrinsic Lexicographic Ordering/Pinch Ratio Clustering). The theoretical foundation for this algorithm, developed in [14], uses ideas from topology (particularly knot theory) suggesting that it should be very flexible and robust with respect to noise. The TILO portion of the algorithm progressively improves a linear ordering of the points in a data set until the ordering satisfies a topological condition called strongly irreducible. The PRC algorithm then divides the data set based on this ordering and a heuristic metric called the pinch ratio. We demonstrate the effectiveness of TILO/PRC for finding clusters in a wide variety of real and synthetic data sets and compare the results to existing clustering methods. Moreover, because the output of TILO depends on the initial ordering, we consider the effects of different random orderings on the final clusters defined by PRC, and show that choosing an initial ordering based on a different clustering algorithm can improve the final clusters. These results verify that both the theoretical foundations of TILO and the heuristic notion of pinch ratio are reasonable.