![]() Therefore, it can occur in any climatic regions including tropical region like Bangladesh 11, 12 or humid climate zone like Malaysia 13, 14. The large variability of precipitation on the deficit side indicates droughts. Meteorological drought frequency does not depend on the average precipitation of an area, rather the variability of precipitation. It is the initiator of all other kinds of droughts and therefore, most widely studies for monitoring droughts 10. Meteorological droughts occur due to deficiency of precipitation from the average. In a simple term, drought is defined as the period of a temporary shortage of water resources due to persistently low precipitation.ĭrought can have different forms, such as meteorological drought, hydrological drought, agricultural drought, and socioeconomic drought 7, 8, 9. The complexity of a drought event is characterized by its duration, intensity, and severity. Drought slowly builds over time and leaves a prolonged influence over a large geographical space without any significant infrastructural damage 5, 6. There is no definite way of defining drought because it is not possible to determine the exact duration of a drought event. It significantly influences water resources availability, agricultural production, environmental health and thus, socio-economy of a region 3, 4. Comparison of the models revealed ELM as the best model in forecasting droughts with minimal RMSE in the range of 0.07–0.85, 0.08–0.76, 0.062–0.80 and 0.042–0.605 for Barisal, Bogra, Faridpur and Mymensingh, respectively for all the SPI scales except one-month SPI for which the RF showed the best performance with minimal RMSE of 0.57, 0.45, 0.59 and 0.42, respectively.ĭrought is a natural disaster that affects society and the environment frequently 1, 2. The results revealed that the proposed models are reliable and robust in predicting droughts in the region. ![]() The model inputs were decided based on correlation statistics and the prediction capability was evaluated using several statistical metrics including mean square error ( MSE), root mean square error ( RMSE), mean absolute error ( MAE), correlation coefficient ( R), Willmott’s Index of agreement ( WI), Nash Sutcliffe efficiency ( NSE), and Legates and McCabe Index ( LM). ![]() Models were developed using monthly rainfall data for the period of 1949–2013 at four meteorological stations namely, Barisal, Bogra, Faridpur and Mymensingh, each representing a geographical region of Bangladesh which frequently experiences droughts. The current research investigated the capability of different versions of relatively well-explored machine learning (ML) models including random forest (RF), minimum probability machine regression (MPMR), M5 Tree (M5tree), extreme learning machine (ELM) and online sequential-ELM (OSELM) in predicting the most widely used DI known as standardized precipitation index (SPI) at multiple month horizons (i.e., 1, 3, 6 and 12). Droughts are usually monitored using drought indices (DIs), most of which are probabilistic and therefore, highly stochastic and non-linear. \), a precipitate of barium sulfate will form.A noticeable increase in drought frequency and severity has been observed across the globe due to climate change, which attracted scientists in development of drought prediction models for mitigation of impacts.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |