Improving Medium-range Dry Lightning Forecasts for Southern California

Dry lightning often results in a significant amount of fire starts in areas where the vegetation is dry and continuous. Meteorologists from the USDA Forest Service Predictive Services' program in Riverside, California are tasked to provide southern and central California's fire agencies with fire potential outlooks. Logistic regression equations were developed by these meteorologists several years ago, which forecast probabilities of lightning as well as lightning amounts, out to seven days across southern California. These regression equations were developed using ten years of historical gridded data from the Global Forecast System (GFS) model on a coarse scale (0.5 degree resolution), correlated with historical lightning strike data. These equations capture lightning episodes (3-5 consecutive days or greater of lightning) well, but perform poorly regarding more detailed information such as exact location and amounts. It is postulated that the inadequacies in resolving the finer details of episodic lightning events is due to the coarse resolution of the GFS data, along with limited predictors. Stability parameters, such as the Lifted Index (LI), the Total Totals index (TT), Convective Available Potential Energy (CAPE), along with Precipitable Water (PW) are the only parameters currently being considered as predictors. It is hypothesized that machine learning techniques applied to a higher resolution historical training dataset will result in an increase in forecast accuracy and detail. We have dynamically downscaled NCEP FNL (Final) Operational Global Analysis data using the Weather Research and Forecasting model (WRF) to 3km spatial and hourly temporal resolution across a decade. Multiple machine learning algorithms, e.g., logistic regression and artificial neural networks, will be trained and tested across this higher vertical, spatial and temporal resolution data set. If successful, we will implement a medium-range lightning prediction model informed by an operational dynamically downscaled GFS forecast product. These forecasts will help fire agencies be better prepared to pre-deploy resources in advance of these events. Specific information regarding duration, amount, and location will be especially valuable.