Search for: All records

An important challenge with Machine Learning (ML) is itstransferability; i.e., whether a ML model trained on one set of data canbe applied to a second set of data without requiring full re-training ofthe model. Transfer Learning (TL) addresses this challenge bytransferring knowledge learned in the source domain (the data it wastrained on) to the target domain (a second set of data that isstatistically different but related, which the model was not trainedon). This study investigates the use of TL for street-scale nuisanceflood forecasting by exploring whether a ML model trained for one set ofstreets can effectively forecast flooding for another set of streets inthe same city. TL is explored using a Long Short-Term Memory (LSTM)model trained on data for the flood-prone streets of Norfolk City,Virginia. The results show that full-weight re-training proved mosteffective and minimal re-training of only the output layer wasinsufficient. The advantage of TL was most pronounced when target datawas limited, meaning data collected at the new water depth sensorlocation included generally less than 18 flood events. As target dataincreased beyond 18 flood events, the benefit of TL diminished relativeto training a ML model directly on the local flood events. Thesefindings can assist cities as they implement street-scale flood sensingsystems to create accurate forecasts for new sensing locations that donot yet have sufficient data records to train a local ML model. 

Reproducible environmental modelling often relies on spatial datasets as inputs, typically manually subset for specific areas. Yet, models can benefit from a data distribution approach facilitated by online repositories, and automating processes to foster reproducibility. This study introduces a method leveraging diverse state-scale spatial datasets to create cohesive packages for GIS-based environmental modelling. These datasets were generated and shared via GeoServer and THREDDS Data Server Connected to HydroShare, contrasting with conventional distribution methods. Using the Regional Hydro-Ecologic Simulation System (RHESSys) across three U.S. catchment-scale watersheds, we demonstrate minimal errors in spatial inputs and model streamflow outputs compared to traditional approaches. This spatial data-sharing method facilitates consistent model creation, fostering reproducibility. Its broader impact allows scientists to tailor the method to various use cases, such as exploring different scales beyond state-scale or applying it to other online repositories using existing data distribution systems, eliminating the need to develop their own.