Nash-Sutcliffe Efficiency Values Research Articles

An improved MUSLE model incorporating the estimated runoff and peak discharge predicted sediment yield at the watershed scale on the Chinese Loess Plateau

An accurate prediction of sediment yield at the watershed scale is critical not only for sustainable watershed management but also for improving knowledge regarding the relationship between sediment yield and its determinant factors, which often rely on the varying model complexity. In this study, a modified sediment yield formula based on the modified universal soil loss equation (MUSLE) model was developed by introducing a channel factor into the original formula. The reliability of the proposed method was tested using data from 1,341 storm events in 38 watersheds and was applied to 256 storm events in five application watersheds using the optimized parameters. Results indicated that the proposed method is very accurate, as demonstrated by the Nash–Sutcliffe efficiency (NSE) values of 88.18 %, 85.72 %, and 85.51 % during calibration, validation, and application, respectively. The performance of the proposed model was superior to that of the original MUSLE model. Subsequently, the proposed method was used to predict sediment yield from the last five typical watersheds. This prediction utilized the parameters derived from the initial 38 watersheds; the peak discharge predicted by the modified Chemicals, Runoff, and Erosion from Agricultural Management Systems (CREAMS); and the runoff estimated by the modified Soil Conservation Service Curve Number (SCS-CN) method. Elevated NSE (61.88–81.42 %) and low root mean square error values (2.35–11.40 t ha−1) were calculated for the five watersheds. From the results, the proposed sediment yield model, combined with the modified SCS-CN method and CREAMS, was found to accurately predict the event-based sediment yield, peak discharge, and runoff in the Loess Plateau region under varying hydrological and geomorphic conditions.

Development of Decision Support System (DSS) for Greenhouse Ventilation and Cooling Control

The confined heat created by the sunlight and ambient temperature is one of the obstacles to greenhouses in the tropics. A conservatory in tropical regions thus requires a proper ventilation and cooling system to provide an ideal greenhouse temperature to support crop production. The main objective of this study is to develop a Decision Support System (DSS) for optimum greenhouse ventilation and cooling control. An equation model to predict the temperature inside was developed by considering heat generation and heat loss inside the greenhouse. The accuracy of the equation model was validated with secondary data from the on-field greenhouse by statistical evaluation metrics. The statistical evaluation proved that the equation model is good with 2.11°C of Root Mean Square Error (RMSE), 6.22% of Percent BIAS (PBIAS) and 0.94 of Nash-Sutcliffe efficiency (NSE) value. A DSS using Microsoft Excel with Visual Basic for Applications (VBA) is developed based on the equation model to provide the ventilation and cooling system information. Input required for the DSS is a climatic condition, dimension and covering greenhouse material. The output of the DSS is the temperature inside the greenhouse, natural ventilation design, forced ventilation, active cooling system design using an evaporative pad and fan, and fogging system. The DSS can be used as an approach for ventilation and cooling design recommendation for the optimum temperature inside the greenhouse.

Evaluating the performance of HBV, HEC-HMS and ANN models in simulating streamflow for a data scarce high-humid tropical catchment in Tanzania

ABSTRACT This study evaluates the performance of the Hydrologic Engineering Center-Hydrologic Modelling System (HEC-HMS), the Hydrologiska Byråns Vattenbalansavdelning (HBV) model, and an artificial neural network (ANN) model in a data-scarce high-humidity tropical catchment. Statistical indices, simulated and observed hydrographs, and flow duration curves were employed for evaluating and comparing their performances. The results indicate that the HEC-HMS model is superior, with Nash–Sutcliffe efficiency (NSE) and coefficient of determination (R2) values of 0.80 and 0.82 for calibration and 0.84 and 0.79 for validation, respectively. The HBV model is also suitable for simulating catchment hydrology, with NSE and R2 values of 0.73 and 0.74 for calibration and 0.64 and 0.64 for validation, respectively. The ANN model performed satisfactorily, with NSE and R2 values of 0.66 and 0.67 for calibration, and 0.55 and 0.52 for validation, respectively. These findings provide insight into the effectiveness of hydrological models, which is important for effective water resources management in light of climate change impacts in the region.

Evaluation of three gridded potential evapotranspiration datasets for streamflow simulation in three inland river basins in the arid Hexi Corridor, Northwest China

Study regionThis study focuses on three data-limited inland river basins in the arid Hexi Corridor, Northwest China. Study focusThe lack of ground-based observation data for estimating potential evapotranspiration (PET) usually limits the streamflow simulation. This study explored the feasibility of using three gridded PET datasets (GLDAS, GLEAM, and ERA5) to force the hydrologic model. The hydrologic performance of these PET datasets was investigated using the HBV-light model. New hydrological insights for the regionThe results show that GLEAM performs best in estimating PET on both a daily and monthly scale. GLDAS generally captures the seasonal variations and patterns well but shows a higher estimation in magnitude. For the hydrological simulation, all three PET datasets can be used as forcing data to drive the HBV-light model, as the Nash-Sutcliffe efficiency (NSE) values are greater than 0.64 during the validation period for the three PET inputs in the three basins. The magnitude and temporal signal of PET forcing data do not significantly affect streamflow simulations of the HBV-light. The model mainly adjusts the water content of the soil box (WCS) to eliminate the efficiency loss caused by the PET magnitude difference to achieve the best simulation results.

Calibrating a Hydrological Model in an Ungauged Mountain Basin with the Budyko Framework

Calibrating spatially distributed hydrological models in ungauged mountain basins is complicated due to the paucity of information and the uncertainty in representing the physical characteristics of a drainage area. In this study, an innovative method is proposed that incorporates the Budyko framework and water balance equation derived water yield (WYLD) in the calibration of the Soil and Water Assessment Tool (SWAT) with a monthly temporal resolution. The impact of vegetation dynamics (i.e., vegetation coverage) on Budyko curve shape parameter ω was considered to improve the Budyko calibration. The proposed approach is applied to the upstream Lancang-Mekong River (UL-MR), which is an ungauged mountain basin and among the world’s most important transboundary rivers. We compared the differences in SWAT model results between the different calibration approaches using percent bias (PBIAS), coefficient of determination (R2), and Nash–Sutcliffe efficiency (NSE) coefficient. The results demonstrated that the Budyko calibration approach exhibited a significant improvement against an unfitted priori parameter run (the non-calibration case) though it did not perform as good as fitting of the calibration by the observed streamflow. The NSE value increased by 44.59% (from 0.46 to 0.83), the R2 value increased by 2.30% (from 0.87 to 0.89) and the PBIAS value decreased by 55.67% (from 39.7 to 17.6) during the validation period at the drainage outlet (Changdu) station. The outcomes of the analysis confirm the potential of the proposed Budyko calibration approach for runoff predictions in ungauged mountain basins.

Rice Productivity Estimation Using Remote Sensing Method

The calculation of crop productivity has now been facilitated by technological development using remote sensing technology or data generated by satellites. Determining the value of productivity using images will shorten the time and does not require much effort. A remote sensing model that connects satellite image reflectance data with rice plant parameters will be handy for monitoring biomass growth and predicting crop yields more quickly and efficiently. This study aimed to determine the regression equation to estimate the productivity of regional rice in Harau District, Lima Puluh Kota Regency. This study consisted of several stages: data collection, data processing, and calculation of rice productivity, NDVI regression analysis with rice productivity, and Nash-Sutcliffe Efficiency (NSE) test against the obtained equations. The regression equation obtained from the results of data analysis to estimate rice productivity in Harau District, Lima Puluh Kota Regency is y = - 82152x4 + 208465x3 - 197654x2 + 82986x - 13014, with an NSE value of 0.64 which is categorized as ‘sufficient’.Keywords: MODIS, NDVI, Rice, Remote sensing; Productivity

Application of a Hybrid CEEMD-LSTM Model Based on the Standardized Precipitation Index for Drought Forecasting: The Case of the Xinjiang Uygur Autonomous Region, China

Accurate forecasting of droughts can effectively reduce the risk of drought. We propose a hybrid model based on complementary ensemble empirical mode decomposition (CEEMD) and long short-term memory (LSTM) to improve drought prediction accuracy. Taking the Xinjiang Uygur Autonomous Region as an example, the prediction accuracy of the LSTM and CEEMD-LSTM models for the standardized precipitation index (SPI) on multiple timescales was compared and analyzed. Multiple evaluation metrics were used in the comparison of the models, such as the Nash–Sutcliffe efficiency (NSE). The results show that (1) with increasing timescale, the prediction accuracy of the LSTM and CEEMD-LSTM models gradually improves, and both reach their highest accuracy at the 24-month timescale; (2) the CEEMD can effectively stabilize the time-series, and the prediction accuracy of the hybrid model is higher than that of the single model at each timescale; and (3) the NSE values for the hybrid CEEMD-LSTM model at SPI24 were 0.895, 0.930, 0.908, and 0.852 for Fuhai, Kuerle, Yutian, and Hami station, respectively. This indicates the applicability of the hybrid model in the forecasting of drought.

Sediment Yield Modeling and Mapping of the Spatial Distribution of Soil Erosion-Prone Areas

Sediment movement is the most critical problem in Ethiopia, notably in the Ketar River watershed, which is located in the Rift Valley Basin. The Ketar River flows through rugged terrain with steep slopes and high sediment movement. The purpose of the study is to evaluate the Soil and Water Assessment Tool's (SWAT) ability to simulate sediment and to identify areas that are vulnerable to soil erosion. This will aid water resource planners in determining the appropriate corrective action. In SWAT sediment sensitivity analysis, the USLE soil erodibility factor (USLE-K) is found to be the most sensitive sediment parameter. The SWAT model sediment simulation performance is evaluated using the coefficient of determination (R2) and Nash-Sutcliffe Efficiency (NSE). The model performance results in R2 and NSE values of 0.69 and 0.55 for calibration and 0.73 and 0.51 for validation, respectively, using the SWAT Calibration and Uncertainty Program (SWAT-CUP). The sediment-prone area subbasins have steep slopes and were mostly covered by cultivated land. Annual sediment yield from cultivated land was approximately 1872.12 t/y, while yield for moderately cultivated grassland was 171.45 t/y. Woodland and forest land have less soil erosion rate. The subbasin highly covered by Eutric Nitisols is found in very high soil erosion-prone areas. Sediment yield from a slight slope is almost zero, whereas sediment yield from steep and very steep slopes is very high. The slope of the subbasin is an important factor in determining sediment yield, followed by land cover and soil types. The very high sediment yield rate area accounted for 39.64% of the total subbasin and it needs soil conservation planning.

The effects of antecedent dry days and land use types on urban runoff quality in a semi-Arid region

ABSTRACT This study simulated the effects of land-use changes on runoff pollution in a catchment of Tehran, Iran. The catchment has a semi-arid climate, a relatively long period from dry summer to rainy autumn and highly varying precipitation levels. Urban runoff samples were collected from six stations including five different land-based activities and a mixed land-use, which supported all land-use types. Event Mean Concentration (EMC) was applied to determine the Nonpoint Source (NPS) pollution of urban runoff such as Total Suspended Solid (TSS), Total Nitrogen (TN), Total Phosphorus (TP) and heavy metals, including zinc (Zn), copper (Cu) and lead (Pb), in five land-uses. Sampling was performed during five events with different Antecedent Dry Days (ADDs) in time period 2019-2020. The Storm Water Management Model (SWMM) was employed to simulate the quality of urban runoff base on measured EMCs in each event for the different parameters under investigation and the average of measured EMCs. The results illustrated that that the maximum and minimum amount of EMCs were pertained to the events with 115 and 1 dry days respectively. While, daily simulation of runoff pollution based on measured amount of EMCs in the catchment indicated that the calibration criteria such as Root Mean Square Error (RMSE), Normalized Objective Function (NOF), Nash-Sutcliffe Efficiency (NSE) and R 2 were very good for the minimum amount of EMCs and satisfactory for the average of EMC`s calculated, NSE values was not satisfactory for the maximum amount of EMCs. Uncertainty of ADDs can significantly affect the results of the maximum EMC simulation. This study also found higher TSS and TP concentrations in runoff in open space land-use and significantly higher heavy metals and TN concentrations in runoff in the industrial land-use compared with other land-use types in the catchment.

TREND ANALYSIS OF RIVER FLOW IN LANGAT RIVER BASIN USING SWAT MODEL

The increase in population and the human activities in this basin area has led to many water shortage problems. This research was carried out to investigate the impacts of land-use changes and urbanization on water discharge in Langat River Basin using ArcGIS. It was applied using the Soil Water Assessment Tool (SWAT). This research aimed to identify how critical land-use changes and the increment of the population in Langat River Basin could impact the water discharge. The rainfall, humidity, solar, wind speed data from 2010 – 2016 were used for modelling purposes. The results obtained from calibrated results were satisfactory, with the value of the coefficient of determination of 0.63 and the value of Nash-Sutcliffe Efficiency (NSE) of 0.69. The precipitation and river flow pattern observed shows decreasing in the river flow from May to September 2016 and increased in November to December 2016. It can be observed that the river flow decreased due to some factors, and this may be a concerning issue as Langat River Basin is used to supply water to people in Klang Valley. This paper has proven that the GIS technology and Arc SWAT model can simulate the streamflow in Langat River Basin and can be further demonstrated to other basins. The model also can be used for further analysis and for in the future.

Performance evaluation of infiltration models under different tillage operations in a tropical climate

Land management practices have the propensity to influence soil infiltration characteristics and predictability of infiltration models. This study was conducted to evaluate the performances of the Kostiakov model, the Philip model and the Horton model in predicting cumulative infiltration depth under four tillage systems in a sandy clay loam: (i) No Tillage (NT), (ii) Reduced Tillage (RT), (iii) Ploughing followed by Harrowing and Ridging (PHR), and (iv) Deep tillage followed by Ploughing, Harrowing and Ridging (DPHR). Using the double ring infiltrometer to measure the infiltration rate, the observed data was fitted to the infiltration models and their goodness of fit was verified by Root Mean Square Error (RMSE), Mean Absolute Error (MAE), coefficient of determination (R2), Nash Sutcliffe efficiency (NSE) and paired sample t-test. The results show that the Kostiakov model exhibited the highest accuracy with the highest R2 and NSE values (R2≥0.9967 and NSE ≥ 0.9965) and lowest errors (RMSE≤ 1.16 mm and MAE ≤ 0.98 mm). The comparison of the performances of the models in predicting the cumulative infiltration depth revealed that the Kostiakov model is superior to the Philip and the Horton models under all the Tillage systems, as the Philip and the Horton models underestimated and overestimated the observed data at the initial and latter parts of the experiment, respectively. The observed and predicted cumulative infiltration depth compared using the paired sample t-test showed that the Kostiakov model was better than the Horton and the Philip models under NT, RT and PHR, while the Horton model predicted better on the DPHR than the Kostiakov and the Philip models. The infiltration capacities of the conservation tillage practices (NT and RT) were higher than the conventional tillage conditions (PHR and DPHR). However, the performance of the evaluated models in predicting cumulative infiltration shows that the measured infiltration was best simulated for the DPHR followed by the PHR, RT and NT tillage practices. From our study the Kostiakov model precisely predicted the cumulative infiltration depth relative to the Horton and Philip models. It is, therefore, the preferred choice for modelling cumulative infiltration depth in the ochrosols of the study area and under verified field conditions, these models can be applied to determine the suitable infiltration characteristics to minimise deep percolation and run off losses in irrigation scheduling.

The Use of NDVI Algorithm in Predicting the Productivity of Rice Fields of Talang District of Solok Regency

Estimates of rice production carried out in conventional ways require high costs and a long time, when compared to remote sensing technology. Surveying land conditions using remote sensing satellite technology besides the time of obtaining information is fast and cheap, as well as the survey area is wide and the information got is more sustainable. This study aims to predict the productivity of crop yields (crop yield) of rice fields using the NDVI (Normalized Difference Vegetation Index) algorithm. Research conducted by methods of observation and data processing comprises several stages, namely data pre-processing, analysis of index vegetation until extracted, followed by making a working map for observation and validation of the field. Field results as a consideration of the correlation of the value of vegetation index to the phase of growth and average productivity in the area. The results of the analysis showed the value of NDVI observed as a sign of production that occurred was in the generative phase 2 in the 2nd week of July based on trends that occurred in Talang district of Solok Regency. The results of the actual production data validation test and the use of the NDVI algorithm resulted in an NSE (Nash-Sutcliffe Efficiency) value of 0.868 with the category “Good”.

Can slope adjusted Curve Number models compensate runoff underestimation in steep watersheds?: A study over experimental plots in India

The Natural Resources Conservation Service - Curve Number (NRCS-CN) model was originally developed to simulate runoff from a given storm on small agricultural watersheds having mild terrain slope (≤5%), but it has been applied in diverse field conditions and even much beyond its intended scope. The use of published CN table without slope adjustment and with a fixed initial abstraction ratio (λ = 0.2) has resulted in severe underestimation of runoff. In this study, the effect of slope on CN and λ was investigated using the measured rainfall-runoff data from small experimental plots in India. The investigation corroborated the requirement of a slope-adjusted CN equation suited for Indian hydro-climatic conditions, so three slope-adjusted CN models (CN2θ) having λ decaying with slope (θ) were proposed to improve the surface runoff prediction. The proposed models were calibrated and validated using 390 and 127 rainfall-runoff events, respectively, from 39 plots having different land-uses and slopes varying from 5% to 16%. The performance of new models was evaluated using Nash-Sutcliffe Efficiency (NSE), Coefficient of Determination (R2), Normalized Root Mean Square Error (nRMSE), Mean Bias Error (mBIAS), and 1:1 plot. The proposed models exhibited superior performance statistics to existing CN adjustment models for both λ = 0.2 and 0.03. Also, the use of proposed CN2θ significantly improved the values of NSE, R2, nRMSE, mBIAS and regression slope from −0.37, 0.33, 0.960, 10.72 mm and 0.335 to 0.53, 0.61, 0.562, −0.40 mm and 0.865, respectively, as compared to handbook CN values without any slope adjustment.

Development of a lucerne model in APSIM next generation: 2 canopy expansion and light interception of genotypes with different fall dormancy ratings

Lucerne (Medicago sativa L.) canopy expansion, as quantified by leaf area index (LAI), is the crop process that determines the amount of intercepted total radiation during each regrowth cycle. A challenge is to capture seasonal changes of canopy expansion rate in response to the environment. This research integrates parameters and functions of lucerne canopy expansion into the Agricultural Production Systems sIMulator (APSIM) next generation (APSIM NextGen) model (LeafArea module) to simulate canopy expansion and light interception. Over 20 years of detailed field experimental datasets, with multiple treatments, from Lincoln University were used for model development. Functions derived from a fall dormancy (FD) 5 rated genotype were grown under an industry standard defoliation treatment to parametrize the model. These functions were tested further using genotypes with an FD2 or FD10 rating under longer and shorter defoliation regimes, all under irrigated conditions. The APSIM NextGen lucerne model predicted the LAI expansion pattern in each growth cycle as a double sigmoid curve requiring functions that define the lag phase, basal bud initiation, the linear leaf area expansion rate (LAER; m2 m-2 °Cd), and canopy senescence which represents the loss of LAI over time. LAI was well predicted for experiments under the standard (42-day) and long (84 day) defoliation treatments for FD5, with Nash-Sutcliffe efficiency (NSE) of 0.61 and 0.55. However, the derived parameters and functions overestimated LAI under an extreme short defoliation treatment (28-day), NSE values ranged from 0.38 to 0.78. LAER was lower for the short-defoliation intervals (28-day), probably due to a depletion of carbon and nitrogen reverses in perennial organs. For FD2 and FD10, different LAER functions were generated from field observed data and used to improve simulation agreement. There was fair agreement for the 84-day treatment (NSE of 0.32) and the 42-day treatment (NSE of 0.38), but poor agreement for the 28-day treatment for FD10 (NSE = −0.88). The estimated extinction coefficient (k) was the same for seedling and regrowth crops, and consistent across defoliation treatments and FD classes. With the LeafArea module and k value, the APSIM NextGen lucerne model can now estimate daily LAI and intercepted radiation. Future model development includes validating the LeafArea module in different environments. However, a more mechanistic model approach is required to link canopy expansion to carbon and nitrogen reserves in lucerne plants that experience intense defoliation.

Modeling-Based Energy Performance Assessment and Validation of Air-To-Water Heat Pump System Integrated with Multi-Span Greenhouse on Cooling Mode

The purpose of this study was to conduct a modeling-based energy performance assessment and validation of an air-to-water heat pump (AWHP) system, in the cooling mode, integrated with a multi-span greenhouse using TRNSYS software. We used the building energy simulation (BES) model to investigate the performance characteristics of the AWHP system for greenhouse cooling. We modelled the components of the AWHP system, including the fan coil unit (FCU), water storage tank, and water circulation pump integrated with the greenhouse model. The proposed model included all the components of the experimental system. We validated the proposed model by comparing the simulation results with those obtained from field experiments. We investigated the cooling energy supply to the multi-span greenhouse, greenhouse internal air temperature, heat pump (HP) output temperature, and coefficient of performance (COP). We evaluated the performance of our model by calculating the Nash–Sutcliffe efficiency (NSE) coefficient of all the validated components. Furthermore, we performed linear regression analyses (R2) to determine the relationship between the different parameters. NSE values of 0.87, 0.81, and 0.93, for the greenhouse internal air temperature, the energy supply to the greenhouse, and the HP output water temperature, respectively, validated the prediction accuracy of the model. Moreover, R2 values of 0.83 and 0.39 indicated that cooling loads are more dependent on ambient solar radiation than ambient air temperature. Furthermore, an R2 value of 0.91 showed a linear relationship between the HP’s energy consumption and ambient air temperature. The average daily COP of the HP system was 2.9. Overall, the simulation results showed acceptable correlation with the experimental results. The high NSE values validated the high predictive power of the model. The proposed validation model can be used to improve the performance of systems by optimizing the control strategies and capacities of the equipment (e.g., the HP, the FCU, and the area of the greenhouse). We have provided detailed information to enable engineers, researchers, and consultants to implement the model for their specific needs.

Identification of soil erosion hot-spot areas for prioritization of conservation measures using the SWAT model in Ribb watershed, Ethiopia

Soil erosion is one of the pressing environmental problem in Ethiopia Thus, identifying soil erosion hot-spot areas of a watershed/basin and isolating best management practices (BMPs) for soil erosion-prone sub-watersheds is imperative for effective soil loss reduction and lessening its on-site and off-site effects. The present study aimed to identify erosion hot-spot areas for prioritization of conservation measures and evaluate BMPs for reducing soil erosion using the Soil and Water Assessment Tool (SWAT) model in Ribb watershed, Ethiopia. The SWAT model was calibrated (1995–2002) and validated (2003–2008) using flow and sediment data in the SWAT Calibration and Uncertainty Program (SWAT-CUP). The NSE (Nash–Sutcliffe efficiency), R 2 (Coefficient of determination), PBIAS (Percent bias) and RSR (Root Mean Square Error — observations standard deviation ratio) values during flow and sediment calibration and validation periods ranged from 0.7 to 0.9, 0.71 to 0.92, -0.4% to 15.2% and 0.32 to 0.55, respectively, indicating that SWAT is able to simulate streamflow and sediment with sufficient accuracy. The calibrated and validated SWAT model was used to evaluate the effectiveness of three BMPs against the baseline conditions for reducing soil erosion, such as filter strips Scenario (Scenario F), stone/soil bunds Scenario (Scenario S) and reforestation Scenario (Scenario R). The result indicated that about 95% of the watershed are indentified as soil erosion hot-spot areas, which experienced sediment yield > 11 t ha − 1 yr − 1 . The mean annual sediment yield (1995–2008) of the watershed at the baseline conditions was nearly 29 t ha − 1 yr − 1 . The implementation of Scenario F, Scenario S and Scenario R reduced the baseline sediment yield by 28%, 76% and 62% at the watershed scale, respectively. At the sub-watershed levels, Scenario S and Scenario R reduced the mean annual sediment yield from 45%–90% and 0%–90%, respectively. Therefore, the study suggests implementations of Scenario S and Scenario R for effective soil erosion reduction in the study watershed in particular and to other watersheds in Ethiopia in general which have similar environmental settings. • SWAT was applied to identify soil erosion hot-spot areas and evaluate BMPs. • Filter strips, stone/soil bunds and reforestation Scenarios were evaluated. • About 95% of the watershed are identified as soil erosion hot-spot areas. • Stone/soil bunds (76%) and reforestation (62%) Scenarios reduced maximum sediment. • Implementations of stone/soil bunds and reforestation Scenarios are suggested.

A Single Subject, Feasibility Study of Using a Non-Contact Measurement to "Visualize" Temperature at Body-Seat Interface.

Measuring temperature changes at the body-seat interface has been drawing increased attention from both industrial and scientific fields, due to the increasingly sedentary nature from daily leisure activity to routine work. Although contact measurement is considered the gold standard, it can affect the local micro-environment and the perception of sitting comfort. A non-contact temperature measurement system was developed to determine the interface temperature using data gathered unobtrusively and continuously from an infrared sensor (IRs). System performance was evaluated regarding linearity, hysteresis, reliability and accuracy. Then a healthy participant sat for an hour on low/intermediate density foams with thickness varying from 0.5–8 cm while body-seat interface temperature was measured simultaneously using a temperature sensor (contact) and an IRs (non-contact). IRs data were filtered with empirical mode decomposition and fractal scaling indices before a data-driven artificial neural network was utilized to estimate the contact surface temperature. A strong correlation existed between non-contact and contact temperature measurement ( > 0.85) and the estimation results showed a low root mean square error (RMSE) (<0.07 for low density foam and <0.16 for intermediate density foam) and high Nash-Sutcliff efficiency (NSE) values (≈1 for both types of foam materials).

Least square support vector machine-based variational mode decomposition: a new hybrid model for daily river water temperature modeling.

Machines learning models have recently been proposed for predicting rivers water temperature (Tw) using only air temperature (Ta). The proposed models relied on a nonlinear relationship between the Tw and Ta and they have proven to be robust modelling tools. The main motivation for this study was to evaluate how the variational mode decomposition (VMD) contributed to the improvement of machines learning performances for river Tw modelling. Measured data collected at five stations located in Poland from 1987 to 2014 were acquired and used for the analysis. Six machines learning models were used and compared namely, K-nearest neighbor's regression (KNNR), least square support vector machine (LSSVM), generalized regression neural network (GRNN), cascade correlation artificial neural networks (CCNN), relevance vector machine (RVM), and locally weighted polynomials regression (LWPR). The six models were developed according to three scenarios. First, the models were calibrated using only the Ta as input and obtained results show that the models were able to predict consistently water temperature, showing a high determination coefficient (R2) and Nash-Sutcliffe efficiency (NSE) with values near or above 0.910 and 0.915, respectively, and in overall the six models worked equally without clear superiority of one above another. Second, the air temperature was combined with the periodicity (i.e., day, month and year number) as input variable and a significant improvement was achieved. Both models show their ability to accurately predict river Tw with an overall accuracy of 0.956 for R2 and 0.955 for NSE values, but the LSSVM2 have some advantages such as a small errors metrics, and high fitting capabilities and it slightly surpasses the others models. Thirdly, air temperature was decomposed into several intrinsic mode functions (IMF) using the VMD method and the performances of the models were evaluated. The VMD parameters appeared to cause much influence on the prediction accuracy, exhibiting an improvement of about 40.50% and 39.12% in terms of RMSE and MAE between the first and the third scenarios, however, some models, i.e., GRNN and KNNR have not benefited from the VMD. This research has demonstrated the high capability of the VMD algorithm as a preprocessing approach in improving the accuracies of the machine learning models for river water temperature prediction.

Runoff Estimation in the Upper Reaches of the Heihe River Using an LSTM Model with Remote Sensing Data

Runoff estimations play an important role in water resource planning and management. Many accomplishments have been made in runoff estimations based on data recorded at meteorological stations; however, the advantages of the use of remotely sensed data in estimating runoff in watersheds for which data are lacking remain to be investigated. In this study, the MOD13A2 normalized difference vegetation index (NDVI), TRMM3B43 precipitation (P), MOD11A2 land–surface temperature (LST), MOD16A2 evapotranspiration (ET) and hydrological station data were used as data sources with which to estimate the monthly runoff through the application of a fully connected long short–term memory (LSTM) model in the upstream reach of the Heihe River basin in China from 2001 to 2016. The results showed that inputting multiple remote sensing parameters improved the quality of runoff estimation compared to the use of rain gauge observations; an increase in R2 from 0.91 to 0.94 was observed from the implementation of this process, and Nash–Sutcliffe efficiency (NSE) showed an improvement from 0.89 to 0.93. The incorporation of rain gauge data as well as satellite data provided a slight improvement in estimating runoff with a respective R2 value of 0.95 and NSE value of 0.94. This indicates that the LSTM model based on remote sensing data has great potential for runoff estimation, and data obtained by remote sensing technology provide an alternative approach for estimating runoff in areas for which available data are lacking.

Application and assessment of a downscaled GPM dataset in the simulation of snowmelt runoff in alpine mountainous areas

Study regionthe Jingou River basin (located in central Xinjiang, China). Study focusEstimating snowmelt runoff in alpine areas lacking monitoring stations is essential for water resource management. The newly released global precipitation measurement (GPM) data provide a high-precision precipitation input data source for snowmelt runoff simulations in such areas. However, the resolution (10 km × 10 km) is still insufficient for small and medium watersheds, which reduces the application efficiency of the GPM dataset in runoff simulations. Therefore, the geographic weighted regression model (GWR) is used to downscale the GPM dataset and drive the snowmelt runoff model (SRM) in this study. New hydrological insights for the regionThe results show that the average R2 values of daily runoff simulated by observed precipitation data and the downscaled GPM dataset (1 km × 1 km) are 0.869 and 0.847, respectively, and the average Nash-Sutcliffe efficiency (NSE) values are 0.795 and 0.715, respectively. The accuracy of the runoff data simulated by the downscaled GPM dataset is 2.5% lower than that simulated based on the observed data, and good results are obtained. This study shows that the downscaled GPM dataset can be regarded as an effective alternative product in areas lacking observed data. The GPM dataset has good application prospects as substitute data in mountainous areas, and the GPM dataset resolves the precipitation data scarcity in high-elevation mountainous areas without stations and provides a rare data source for modeling.