Search

Floods cause significant damage to human life, infrastructure, agriculture, and the economy. Predicting peak runoffs is crucial for hazard assessment, but it is challenging in remote areas like the Andes due to limited hydrometeorological data. We utilized a 300 km2 catchment over the period 2015–2021 to develop runoff forecasting models exploiting precipitation information retrieved from an X-band weather radar. For the modeling task, we employed the Random Forest (RF) algorithm in combination with a Feature Engineering (FE) strategy applied to the radar data. The FE strategy is based on an object-based approach, which derives precipitation characteristics from radar data. These characteristics served as inputs for the models, distinguishing them as "enhanced models" compared to "referential models" that incorporate precipitation estimates from all available pixels (1210) for each hour. From 29 identified events, enhanced models achieved Nash-Sutcliffe efficiency (NSE) values ranging from 0.94 to 0.50 for lead times between 1 and 6 h. A comparative analysis between the enhanced and referential models revealed a remarkable 23% increase in NSE-values at the 3 h lead time, which marks the peak improvement. The enhanced models integrated new data into the RF models, resulting in a more accurate representation of precipitation and its temporal transformation into runoff. [ABSTRACT FROM AUTHOR]

A laser-optical disdrometer served as reference to assess the absolute percent bias of calculated rainfall intensity using the data of different-resolution tipping-bucket rain gauges classically applied by climatologists and hydrologists in the Andean region. Additionally, the impact of the calculation method (tip counting versus cubic spline interpolation) was examined. The combined effect was assessed for different rainfall intensity classes (0-0.99, 1-1.99, 2-4.99, and 5-10 mm.h-1) and timescales (5, 10, 30, and 60 min). Additionally, the variation in percent absolute bias of the Davis rain gauge, the collector most widely used in the study region, was defined with respect to the Texas rain gauge along an elevation gradient between 3300 and 4000 m a.s.l. Results reveal that the value of the percent absolute bias is largest for small rainfall intensities (≼2 mm.h-1) and short timescales (≼10 min), and decreases when the cubic spline interpolation is used. No relation was found between the error, the elevation, and rainfall depth along the gradient. Based on the research findings, it is recommended to measure precipitation in the high Andean mountain region with a high-resolution sensor and to consider cubic spline for the computation of intensities. [ABSTRACT FROM AUTHOR]

Flash-flood forecasting has emerged worldwide due to the catastrophic socio-economic impacts this hazard might cause and the expected increase of its frequency in the future. In mountain catchments, precipitation-runoff forecasts are limited by the intrinsic complexity of the processes involved, particularly its high rainfall variability. While process-based models are hard to implement, there is a potential to use the random forest algorithm due to its simplicity, robustness and capacity to deal with complex data structures. Here a step-wise methodology is proposed to derive parsimonious models accounting for both hydrological functioning of the catchment (e.g., input data, representation of antecedent moisture conditions) and random forest procedures (e.g., sensitivity analyses, dimension reduction, optimal input composition). The methodology was applied to develop short-term prediction models of varying time duration (4, 8, 12, 18 and 24 h) for a catchment representative of the Ecuadorian Andes. Results show that the derived parsimonious models can reach validation efficiencies (Nash-Sutcliffe coefficient) from 0.761 (4-h) to 0.384 (24-h) for optimal inputs composed only by features accounting for 80% of the model's outcome variance. Improvement in the prediction of extreme peak flows was demonstrated (extreme value analysis) by including precipitation information in contrast to the use of pure autoregressive models. [ABSTRACT FROM AUTHOR]