Esmaiil Mokari

Accurate rainfall-runoff modeling is crucial for water resource management. However, the available models require more field-measured data to produce accurate results, which has been a long-term issue in hydrological modeling. Machine learning (ML) models have shown superiority in the hydrological field over statistical models. The primary aim of the present study was to advance a new coupled model combining model-driven models and ML models for accurate rainfall-runoff simulation in the Voshmgir basin in northern Iran. Rainfall-runoff data from 2002 to 2007 were collected from the tropical rainfall measuring mission (TRMM) satellite and the Iran water resources management company. The findings revealed that the model-driven model could not fully describe river runoff patterns during the investigated time period. The extreme learning machine and support vector regression models showed similar performances for 1-day-ahead rainfall–runoff forecasting, while the long short-term memory (LSTM) model outperformed these two models. Our results demonstrated that the coupled physically based model and LSTM model outperformed other models, particularly for 1-day-ahead forecasting. The present methodology could be potentially applied in the same hydrological properties catchment.

The Moderate Resolution Imaging Spectroradiometer (MODIS) level-3 chlorophyll-a (Chl-a) product is one of the widely used ocean colour products that is often used for water quality monitoring of marine ecosystems. However, this product includes a large amount of missing data due to high surface reflectance and cloudy conditions that inevitably affect its suitability for spatiotemporal analysis of water quality. The objective of this study was to compare four Machine Learning (ML) techniques including K-nearest neighbour (KNN), Support Vector Regression (SVR), Random Forest Regression (RFR), and Artificial Neural Network (ANN) with well-known Data Interpolation Empirical Orthogonal Function (DINEOF) method for spatiotemporal missing imputation of MODIS Chl-a. The Southern Caspian Sea, which has a high Chl-a concentration, was selected as the case study. A cross-validation approach ranging missing data ratio from 0.1 to 0.8 was implemented to investigate the optimal parameters of the models and compare their performance for missing imputation. The results indicated that all ML models, except KNN, outperformed the DINEOF method for missing imputation of MODIS Chl-a. The SVR with the highest accuracy and the lowest variability of errors had the best performance among the five competing models, while the KNN showed the worst performance. The main reason for the better accuracy of the SVR than the other models is its structural risk minimization procedure that leads to the better generalization of the SVR model. The current results showed that the ML techniques used in the current study, the SVR in particular, are able to produce reliable imputations of the MODIS Chl-a missing data and can be a useful tool in water quality monitoring of marine ecosystems.

Core Ideas: Pecan is a vitally important specialty crop in the southwestern United States. No study is available on modeling temporal variability of NO ₃ –N transport in pecan orchards. Hydrus‐1D predicted well water and NO ₃ –N variability by depth for a heavy textured soil. NO ₃ –N balance identified denitrification contributing to major loss. Nitrogen management in pecan orchards should take into account on and off years to decrease leaching. Pecan [( Carya illinoinensis (Wangenh.) K. Koch] is an important specialty crop in New Mexico. This research quantifies soil water and soil nitrate‐nitrogen (NO ₃ –N) (mg L ⁻¹ of soil) variations with depth, root NO ₃ –N (kg ha ⁻¹ ) uptake, and NO ₃ –N (kg ha ⁻¹ ) balance for the 100‐cm soil profile during two growing seasons in a flood‐irrigated pecan orchard. Nitrate‐nitrogen was determined six times during the growing seasons of 2015 and 2016. The HYDRUS‐1D model was used to optimize the water flow parameters using measured volumetric soil water content (θ). Model calibration and validation for NO ₃ –N included the optimization of reaction parameters for nitrification and denitrification of each soil layer. The results showed that the model simulated θ well (0.44 ≤ d [index of agreement] ≤ 0.73) at different depths during both calibration (2009) and validation (2010) periods. Generally, HYDRUS‐1D simulated soil profile NO ₃ –N concentrations that were correlated with measurements at all depths during both years. Total root NO ₃ –N uptake showed a significant increase of 72% in 2016 compared with 2015. The NO ₃ –N balance showed that ∼40% of applied NO ₃ –N per year was denitrified, which was the main contributor to the NO ₃ –N loss from the soil profile during both years. Nitrate‐nitrogen leaching below the soil profile was 32 and 26% of applied NO ₃ –N in 2015 and 2016, respectively. The fertigation rate was much higher than the plant demand during both years, and it should be decreased to reduce NO ₃ –N losses.