Applying data mining techniques for rainfall modeling because of a lack of sufficient memory components may increase uncertainty in rainfall forecasting. To solve this issue, in this research, a deep-learning-based long short-term memory (LSTM) model is developed for the first time for forecasting monthly rainfall data, and its capability is compared with a random forest (RF) data-driven model. To this end, monthly rainfall data for a period of 41 years (1980–2020) from two meteorological stations in Turkey, namely Rize and Konya, with different climatic conditions, are used. The analysis is carried out using optimum window sizes for determining the optimum lag times of rainfall time series. The performance of the models is evaluated using five statistical measures, namely root mean square error (RMSE), RMSE-observations standard deviation ratio (RSR), Legate and McCabe’s index (LMI), correlation coefficient (R) and Nash–Sutcliffe efficiency (NSE), and also using two visual means, namely Taylor and violin diagrams. The results reveal that the LSTM model, as a more efficient tool, outperforms the RF model in forecasting rainfall at both stations, with improved RMSE of 12.2–14.9%, RSR of 12.3–14.8%, R of 9.4–13.5% and NSE of 32.9–33.2%. The LSTM-based approach proposed herein could be adopted over any global climatic conditions to forecast the monthly rainfall with reasonable accuracy. GRAPHICAL ABSTRACT

This paper belongs to our Special Issue “Application of Climate Data in Hydrologic Models”

In this paper, a potential crack region method is proposed to detect road pavement cracks by using the adaptive threshold. To reduce the noises of the image, the pre-treatment algorithm was applied according to the following steps: grayscale processing, histogram equalization, filtering traffic lane. From the image segmentation methods, the algorithm combines the global threshold and the local threshold to segment the image. According to the grayscale distribution characteristics of the crack image, the sliding window is used to obtain the window deviation, and then, the deviation image is segmented based on the maximum inter-class deviation. Obtain a potential crack region and then perform a local threshold-based segmentation algorithm. Real images of pavement surface were used at the Su Tong Li road in Suzhou, China. It was found that the proposed approach could give a more explicit description of pavement cracks in images. The method was tested on 509 images of the German asphalt pavement distress (Gap) dataset: The test results were found to be promising (precision = 0.82, recall = 0.81, F1 score = 0.83).

Accurate prediction of daily river flow (Q_t) remains a challenging yet essential task in hydrological modeling, particularly crucial for flood mitigation and water resource management. This study introduces an advanced M5 Prime (M5P) predictive model designed to estimate Q_t as well as one- and two-day-ahead river flow forecasts (i.e. Q_t+1 and Q_t+2). The predictive performance of M5P ensembles incorporating Bootstrap Aggregation (BA), Disjoint Aggregating (DA), Additive Regression (AR), Vote (V), Iterative classifier optimizer (ICO), Random Subspace (RS), and Rotation Forest (ROF) were comprehensively evaluated. The proposed models were applied to a case study data in Tuolumne County, US, using a dataset comprising measured precipitation (P_t), evaporation (E_t), and Q_t. A wide range of input scenarios were explored for predicting Q_t, Q_t+1, and Q_t+2. Results indicate that P_t and Q_t significantly influence prediction accuracy. Notably, relying solely on the most correlated variable (e.g., Q_t-1) does not guarantee robust prediction of Q_t. However, extending the forecast horizon mitigates the influence of low-correlation input variables on model accuracy. Performance metrics indicate that the DA-M5P model achieves superior results, with Nash-Sutcliff Efficiency of 0.916 and root mean square error of 23 m³/s, followed by ROF-M5P, BA-M5P, AR-M5P, AR-M5P, RS-M5P, V-M5P, ICO-M5P, and the standalone M5P model. The ensemble M5P modeling framework enhanced the predictive capability of the stand-alone M5P algorithm by 1.2 %–22.6 %, underscoring its efficacy and potential for advancing hydrological forecasting.

Stormwater management is a key issue in line with global problems of urbanization and climate change. Assessing the effectiveness in managing stormwater is crucial to maintain urban resilience to flooding risk. A method based on a stormwater management model (SWMM) was developed for assessing the control of stormwater runoff volume and the percentage removal of suspended solids by implementing a Sponge City strategy. An interdisciplinary approach was adopted incorporating Low Impact Development (LID) with urban green infrastructure and grey infrastructure paradigms in a typical old residential community in Suzhou, China. Sponge facilities for reducing stormwater runoff included bio-retention cells, permeable pavements, grassed pitches, and stormwater gardens. The simulation results of SWMM show that the stormwater pipe system can meet the management standard for storms with a five-year recurrence interval. The volume capture ratio of annual runoff was 91%, which is higher than control target of 80%. The suspended solids reduction rate was 56%, which meets the requirement of planning indicators. Thus, the proposed method of spongy facilities can be used for renovation planning in old residential areas in China. Implementing spongy facilities with a LID strategy for stormwater management can significantly enhance urban water resilience and improve ecosystem services.