Forecasting excessive rainfall with random forests and a deterministic convection-allowing model

Abstract

Approximately seven years of daily initializations from the convection-allowing National Severe Storms Laboratory Weather Research and Forecasting model are used as inputs to train random forest (RF) machine learning models to probabilistically predict instances of excessive rainfall. Unlike other hazards, excessive rainfall does not have an accepted definition, so multiple definitions of excessive rainfall and flash flooding – including flash flood reports and 24-hr average recurrence intervals (ARIs) – are used to explore RF configuration forecast sensitivities. RF forecasts are analogous to operational Weather Prediction Center (WPC) day-1 Excessive Rainfall Outlooks (EROs) and their resolution, reliability, and skill are strongly influenced by rainfall definitions and how inputs are assembled for training. Models trained with 1-y ARI exceedances defined by the Stage-IV (ST4) precipitation analysis perform poorly in the northern Great Plains and southwest U.S., in part due to a high bias in the number of training events in these regions. Increasing the ARI threshold to 2 years or removing ST4 data from training, optimizing forecast skill geographically, and spatially averaging meteorological inputs for training generally results in improved CONUS-wide RF forecast skill. Both EROs and RF forecasts have seasonal skill – poor forecasts in the late fall and winter and skillful forecasts in the summer and early fall. However, the EROs are consistently and significantly better than their RF counterparts, regardless of RF configuration, particularly in the summer months. The results suggest careful consideration should be made when developing ML-based probabilistic precipitation forecasts with convection-allowing model inputs, and further development is necessary to consider these forecast products for operational implementation.

Towards Risk‐Free Trustworthy Artificial Intelligence: Significance and Requirements

“…Science. Te applications of AI and machine learning (ML) in environmental science have recently gained growing popularity [183][184][185][186]. Environmental scientists employ AI/ML to make sense of raw data, e.g., satellite imagery and climate data, in order to come up with appropriate decisions for implementation.…”

Classification of Weather Conditions Based on Supervised Learning for Swedish Cities

“…Hill and Schumacher [7] employed RF, an ensemble learning technique consisting of multiple decision trees, to attain accurate weather predictions. The RF model's strengths, such as its capacity to manage extensive and intricate datasets and its resilience to noise and missing data, make it particularly suitable to address forecasting challenges involving nonlinear relationships and variable interactions.…”

Why we need to focus on developing ethical, responsible, and trustworthy artificial intelligence approaches for environmental science

“…Artificial intelligence (AI) and machine learning (ML) have recently exploded in popularity for a wide variety of environmental science applications (e.g., McGovern et al, 2019; Reichstein et al, 2019; Gagne et al, 2020; Gensini et al, 2021; Hill and Schumacher, 2021; Lagerquist et al, 2021; Schumacher et al, 2021). Like other fields, environmental scientists are seeking to use AI/ML to build a linkage from raw data, such as satellite imagery and climate models, to actionable decisions.…”