Ecological forecasting provides a powerful set of methods for predicting short‐ and long‐term change in living systems. Forecasts are now widely produced, enabling proactive management for many applied ecological problems. However, despite numerous calls for an increased emphasis on prediction in ecology, the potential for forecasting to accelerate ecological theory development remains underrealized. Here, we provide a conceptual framework describing how ecological forecasts can energize and advance ecological theory. We emphasize the many opportunities for future progress in this area through increased forecast development, comparison and synthesis. Our framework describes how a forecasting approach can shed new light on existing ecological theories while also allowing researchers to address novel questions. Through rigorous and repeated testing of hypotheses, forecasting can help to refine theories and understand their generality across systems. Meanwhile, synthesizing across forecasts allows for the development of novel theory about the relative predictability of ecological variables across forecast horizons and scales. We envision a future where forecasting is integrated as part of the toolset used in fundamental ecology. By outlining the relevance of forecasting methods to ecological theory, we aim to decrease barriers to entry and broaden the community of researchers using forecasting for fundamental ecological insight.

Estimates of ground-level ozone concentrations are necessary to determine the human health burden of ozone. To support the Global Burden of Disease Study, we produce yearly fine resolution global surface ozone estimates from 1990 to 2017 through a data fusion of observations and models. As ozone observations are sparse in many populated regions, we use a novel combination of the M3Fusion and Bayesian Maximum Entropy (BME) methods. With M3Fusion, we create a multimodel composite by bias-correcting and weighting nine global atmospheric chemistry models based on their ability to predict observations (8834 sites globally) in each region and year. BME is then used to integrate observations, such that estimates match observations at each monitoring site with the observational influence decreasing smoothly across space and time until the output matches the multimodel composite. After estimating at 0.5° resolution using BME, we add fine spatial detail from an additional model, yielding estimates at 0.1° resolution. Observed ozone is predicted more accurately (R 2 = 0.81 at the test point, 0.63 at 0.1°, and 0.62 at 0.5°) than the multimodel mean (R 2 = 0.28 at 0.5°). Global ozone exposure is estimated to be increasing, driven by highly populated regions of Asia and Africa, despite decreases in the United States and Russia.

Floods are the leading cause of natural disaster damages in the United States, with billions of dollars incurred every year in the form of government payouts, property damages, and agricultural losses. The Federal Emergency Management Agency oversees the delineation of floodplains to mitigate damages, but disparities exist between locations designated as high risk and where flood damages occur due to land use and climate changes and incomplete floodplain mapping. We harnessed publicly available geospatial datasets and random forest algorithms to analyze the spatial distribution and underlying drivers of flood damage probability (FDP) caused by excessive rainfall and overflowing water bodies across the conterminous United States. From this, we produced the first spatially complete map of FDP for the nation, along with spatially explicit standard errors for four selected cities. We trained models using the locations of historical reported flood damage events (n = 71 434) and a suite of geospatial predictors (e.g. flood severity, climate, socio-economic exposure, topographic variables, soil properties, and hydrologic characteristics). We developed independent models for each hydrologic unit code level 2 watershed and generated a FDP for each 100 m pixel. Our model classified damage or no damage with an average area under the curve accuracy of 0.75; however, model performance varied by environmental conditions, with certain land cover classes (e.g. forest) resulting in higher error rates than others (e.g. wetlands). Our results identified FDP hotspots across multiple spatial and regional scales, with high probabilities common in both inland and coastal regions. The highest flood damage probabilities tended to be in areas of low elevation, in close proximity to streams, with extreme precipitation, and with high urban road density. Given rapid environmental changes, our study demonstrates an efficient approach for updating FDP estimates across the nation.

No abstract

geospatial nature of the paper (GEO), and VIS Conference paper type and track (TRK) are shown for each paper. Percentages on the top band (lightest gray bars) correspond to data domain types. The GEO band marks papers as either containing both geospatial data and a geospatial analysis (dark gray) or geospatial data only (light gray). The TRK band is colored by the VIS Conference paper types and tracks listed on Open Access VIS [15].