Transfer learning to improve streamflow forecasts in data sparse regions

by   Roland Oruche, et al.

Effective water resource management requires information on water availability, both in terms of quality and quantity, spatially and temporally. In this paper, we study the methodology behind Transfer Learning (TL) through fine-tuning and parameter transferring for better generalization performance of streamflow prediction in data-sparse regions. We propose a standard recurrent neural network in the form of Long Short-Term Memory (LSTM) to fit on a sufficiently large source domain dataset and repurpose the learned weights to a significantly smaller, yet similar target domain datasets. We present a methodology to implement transfer learning approaches for spatiotemporal applications by separating the spatial and temporal components of the model and training the model to generalize based on categorical datasets representing spatial variability. The framework is developed on a rich benchmark dataset from the US and evaluated on a smaller dataset collected by The Nature Conservancy in Kenya. The LSTM model exhibits generalization performance through our TL technique. Results from this current experiment demonstrate the effective predictive skill of forecasting streamflow responses when knowledge transferring and static descriptors are used to improve hydrologic model generalization in data-sparse regions.


page 4

page 6


Transfer Learning Based Efficient Traffic Prediction with Limited Training Data

Efficient prediction of internet traffic is an essential part of Self Or...

NodeTrans: A Graph Transfer Learning Approach for Traffic Prediction

Recently, deep learning methods have made great progress in traffic pred...

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

Transferring the knowledge learned from large scale datasets (e.g., Imag...

Attention-based Domain Adaptation Forecasting of Streamflow in Data Sparse Regions

Streamflow forecasts are critical to guide water resource management, mi...

Transfer Learning Approaches for Knowledge Discovery in Grid-based Geo-Spatiotemporal Data

Extracting and meticulously analyzing geo-spatiotemporal features is cru...

HistoKT: Cross Knowledge Transfer in Computational Pathology

The lack of well-annotated datasets in computational pathology (CPath) o...

Please sign up or login with your details

Forgot password? Click here to reset