A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Deep Learning‐Based Hydrological Drought Prediction in the Wardha River Basin, India
https://orcid.org/0000-0003-4821-1037
ABSTRACTDrought is an abnormal condition characterized by dry weather which can continue for days, months, and years. Drought often has major effects on the ecosystems and agriculture of vulnerable regions leading to catastrophe on the local economies. Deep learning was employed in this study to forecast hydrological drought in the Wardha River basin in Maharashtra, Vidarbha region, India. Monthly streamflow data from 1971 to 2020 for the Wardha River serve as the basis for analysis. The study calculates the standardized streamflow index (SSI) at several timescales (3, 6, 9, 12, and 24 months). Deep learning models, specifically the long short‐term memory (LSTM) model and the multilayer perceptron (MLP) model, are employed for drought prediction within the study region. The models are trained with data spanning from 1971 to 2005 and tested against data from 2006 to 2020. Predictions are made for lead time scales of 6 and 12 months by considering lagged SSI values. Drought event lead time scale forecasts will serve as an early warning strategy. The 6‐ and 12‐month lead times of the SSI forecast could be used as a warning for anticipated drought conditions. The study assesses model efficiency by comparing the root mean square error (RMSE) and mean absolute error (MAE) between the LSTM and MLP models. The results indicate that the LSTM model performs better for higher time scales in predicting hydrological drought, whereas the MLP model demonstrates superior predictive capabilities for lower time scales of drought index.
Deep Learning‐Based Hydrological Drought Prediction in the Wardha River Basin, India
https://orcid.org/0000-0003-4821-1037
ABSTRACTDrought is an abnormal condition characterized by dry weather which can continue for days, months, and years. Drought often has major effects on the ecosystems and agriculture of vulnerable regions leading to catastrophe on the local economies. Deep learning was employed in this study to forecast hydrological drought in the Wardha River basin in Maharashtra, Vidarbha region, India. Monthly streamflow data from 1971 to 2020 for the Wardha River serve as the basis for analysis. The study calculates the standardized streamflow index (SSI) at several timescales (3, 6, 9, 12, and 24 months). Deep learning models, specifically the long short‐term memory (LSTM) model and the multilayer perceptron (MLP) model, are employed for drought prediction within the study region. The models are trained with data spanning from 1971 to 2005 and tested against data from 2006 to 2020. Predictions are made for lead time scales of 6 and 12 months by considering lagged SSI values. Drought event lead time scale forecasts will serve as an early warning strategy. The 6‐ and 12‐month lead times of the SSI forecast could be used as a warning for anticipated drought conditions. The study assesses model efficiency by comparing the root mean square error (RMSE) and mean absolute error (MAE) between the LSTM and MLP models. The results indicate that the LSTM model performs better for higher time scales in predicting hydrological drought, whereas the MLP model demonstrates superior predictive capabilities for lower time scales of drought index.
Deep Learning‐Based Hydrological Drought Prediction in the Wardha River Basin, India
https://orcid.org/0000-0003-4821-1037
ABSTRACTDrought is an abnormal condition characterized by dry weather which can continue for days, months, and years. Drought often has major effects on the ecosystems and agriculture of vulnerable regions leading to catastrophe on the local economies. Deep learning was employed in this study to forecast hydrological drought in the Wardha River basin in Maharashtra, Vidarbha region, India. Monthly streamflow data from 1971 to 2020 for the Wardha River serve as the basis for analysis. The study calculates the standardized streamflow index (SSI) at several timescales (3, 6, 9, 12, and 24 months). Deep learning models, specifically the long short‐term memory (LSTM) model and the multilayer perceptron (MLP) model, are employed for drought prediction within the study region. The models are trained with data spanning from 1971 to 2005 and tested against data from 2006 to 2020. Predictions are made for lead time scales of 6 and 12 months by considering lagged SSI values. Drought event lead time scale forecasts will serve as an early warning strategy. The 6‐ and 12‐month lead times of the SSI forecast could be used as a warning for anticipated drought conditions. The study assesses model efficiency by comparing the root mean square error (RMSE) and mean absolute error (MAE) between the LSTM and MLP models. The results indicate that the LSTM model performs better for higher time scales in predicting hydrological drought, whereas the MLP model demonstrates superior predictive capabilities for lower time scales of drought index.
Deep Learning‐Based Hydrological Drought Prediction in the Wardha River Basin, India
CLEAN Soil Air Water
Janardhana, Mangala (author) / Kikon, Ayilobeni (author)
2025-01-01
Article (Journal)
Electronic Resource
English
Hydrological Drought in the Upper Nakdong River Basin
| British Library Conference Proceedings | 2010
Seismic Risk Assesment of Wardha City
| Springer Verlag | 2024
Hydrological Drought Analysis in Namhan River Basin, Korea
| British Library Online Contents | 2014