基于两阶段粒子群优化算法的新型逐步分解集成径流预测模型

传统分解集成径流预测模型首先将整个径流序列分解成若干个子序列,再将这些子序列划分为训练期和验证期进行建模,错误地将验证期内预报因子数据视作已知数据处理,难以应用于实际径流预报工作中。并且,这类模型的预测结果仅为一个确定数值,难以描述由于径流序列随机性和波动性而导致的预测不确定性。为解决以上问题,本文结合变分模态分解方法、支持向量机模型和核密度估计方法,提出了一种可同时进行点预测和区间预测的新型逐步分解集成(VMD-SVM-KDE)模型,并提出了一种两阶段粒子群优化(TSCPSO)算法来优化模型参数。选用黄河流域月径流数据评估模型性能,研究结果表明:(1)VMD-SVM-KDE模型将单一SVM-KDE模型的确定系数(R²)和纳什效率系数(NSE)值由0.145~0.630提升至0.872~0.921,区间平均偏差(INAD)值由0.046~95.844降低至0.005~0.034,说明VMD-SVM-KDE模型显著改进了单一SVM-KDE模型的点预测和区间预测性能;(2)相较于一阶段PSO算法,TSCPSO优化算法将单一模型的R²和NSE值由0.145~0.480提升至0.309~0.630,INAD值由48.813~95.844降低至0.046~0.195,将分解集成模型的R²和NSE值由0.872~0.912提升至0.876~0.921,INAD值由0.007~0.034降低至0.005~0.014,说明TSCPSO优化算法可以克服SVM的过拟合问题,并能提高单一模型和分解集成模型的预测精度;(3)VMD-SVM-KDE-TSCPSO有效解决了传统分解集成预测模型存在的错误使用验证期内预报因子数据的问题,并在各站的R²和NSE值均约为0.9,INAD值的范围为0.005~0.014,具有更高的点预测和区间预测精度。文中模型可为优化径流预测模型和非平稳非线性水文序列预报提供新思路。     

基于HJ-1A CCD影像和ELM模型的太湖叶绿素a预测研究

以典型二类水体——太湖为例,基于环境一号遥感影像,构建了基于 ELM模型的叶绿素a浓度预测模型,将预测结果与传统的BP人工神经网络和支持向量机 SVM进行了比较。研究结果表明：ELM模型预测值与实测值之间的R²高达0.911 4,而BP和SVM模型的R²分别为0.366 3和0.744 8,均方根误差RMSE由BP模型和SVM模型的3.728 8 μg/L和2.132 4 μg/L降为ELM模型的1.327 0 μg/L, ELM模型的平均相对误差MRE=2.65％,小于BP模型的6.59%和SVM模型的3.89%;与其他两种方法相比,ELM模型反演太湖水体叶绿素a浓度精度更高,ELM模型参数选择简单,可以显著提高模型的学习速度,不易陷入局部最优值,具有更好的泛化性能;ELM模型可以有效地应用于内陆水体叶绿素a浓度的预测。     

基于SVM的蒸发量预测因子组合与模型研究

为正确认识水面蒸发量与气象因子之间的关系,建立合理的区域性蒸发量预测模型,选择山西长治气象站为研究对象,应用灰色关联分析选择关联度较高的气象因子,以该站2015—2016年日气象数据作为训练样本,分别建立了26个气象因子组合下的蒸发量SVM预测模型,并以2017年日气象数据作为验证样本,对模型模拟结果进行验证。研究表明气象因子组合对模型模拟效果具有重大影响,在长治地区预测日蒸发量的最佳模型所对应的因子组合为日平均温度、日平均风速、日照时数、相对湿度,此时模型预测R2值为0.824,RMSE值为0.403,模拟精度较高。本文所建立的长治市蒸发量预测模型可为蒸发量预测提供重要参考。     

缺资料地区多源降水产品适用性评价——以巴西巴拉那河为例

作为地面站降水监测的补充,以卫星遥感为代表的多源降水产品是准确识别区域特别是缺资料地区降水分布的关键。从时间和空间两个维度,以决定系数（R²）、纳什效率系数（NSE）和相对误差（RE）为评价指标,以地面站实测降水信息为参照,比较评估了CFSv2、ERA5和基于改进model-X knockoffs的随机森林方法遥相关建模形成的降水产品（TPP）在巴西巴拉那河上游流域降水信息识别中的适用性。结果表明：TPP和ERA5预测研究区降水量与实测值拟合精度高于CFSv2产品。时间上,交叉时段3种典型降水产品计算研究区的面雨量与实测值拟合R²和NSE均表现为ERA5>TPP>CFSv2,其中,CFSv2产品存在计算的面雨量较实测值偏大问题,拟合RE为28.2%;ERA5则相反,与实测值拟合RE为-10.3%;TPP产品计算的面雨量与实测值拟合RE最小,仅为0.33%。空间上,3种产品与遴选气象站点实测降水量拟合R²和NSE表现为ERA5>TPP>CFSv2,|RE|则表现为TPP相似文献   

萍乡市城市地表径流污染物浓度变化特征分析及数值模拟

以海绵城市建设试点城市萍乡市地表径流污染物（以SS和TP为代表）浓度变化特征与预测模型适应性为研究对象,根据两场次的降雨资料及实测径流污染物浓度数据,确定所建地表径流污染物浓度变化预测模型Sartor-Boyd和p/r模型的参数,并模拟和分析了地表径流污染物浓度变化过程。结果表明：萍乡市地表径流污染物（SS和TP）浓度受初始冲刷效应的影响,降雨过程前期随雨强的峰值而达到最大,降雨过程后期污染物浓度受雨强的峰值波动影响较小;受模型参数的影响,Sartor-Boyd模型模拟值的统计学指标RPD、R²、NSE均小于p/r模型的相应指标,p/r模型对萍乡市降雨地表径流污染物排放规律的预测精度较好,模型可信度较高。结合萍乡市地区降雨状况建立的p/r数学模型可为该区域海绵城市建设过程中地表径流污染物浓度的预测及管理提供参考。     

玉米光合产物分配与转移模拟方法的研究

光合产物分配与转移的模拟是作物生长模拟的重要组成部分。以山西省文峪河试验站春玉米3个年度（2018、2019和2020年）灌溉试验（高水处理T1和零水处理T2）资料对光合产物分配方法（分配系数法和分配指数法）进行模拟研究。结果表明：从拟合精度来看,两种方法对茎、叶、穗模拟值与实测值的拟合优度R²均大于0.9,其中穗模拟精度最高（R²>0.95）。水分胁迫会导致茎分配指数减小、叶和穗分配指数增大,且穗分配指数受水分胁迫影响最大;水分胁迫主要是通过影响生长相关性（茎叶比、穗茎比和根冠比）来影响分配系数,其中穗茎比随时间变化过程的模拟效果最好（R²=0.882）;茎叶比水分胁迫指数为-0.130,表明水分胁迫会导致茎叶比减小;穗茎比和根冠比的水分胁迫指数分别为0.248和0.143,表明水分胁迫会使穗茎比和根冠比增大;茎、叶、根分配系数在生长前期受水分胁迫影响较小,生长后期水分胁迫导致茎、叶、根分配系数增大以及穗分配系数减小;水分胁迫使光合产物的转移率减小。整体而言,两种方法对光合产物的拟合精度非常接近,但分配系数法对光合产物转移量的模拟结果更接近于实际情况,表明分配系数法具有更好的机理性。     

极限学习机在湖库总磷、总氮浓度预测中的应用

基于传统BP人工神经网络模型训练速度慢、参数选择困难、易陷入局部极值等问题,提出极限学习机(ELM)的水质预测模型。以云南某水库为例,选取NH₃-N、NO₂^--N、NO₃^--N、COD_Mn和水体透明度作为网络输入,TP、TN作为输出, 构建基于ELM的湖库TP、TN预测模型,并将ELM预测结果与传统BP、GA-BP、RBF人工神经网络模型模拟结果进行比较。结果表明,ELM模型预测精度高于传统BP和RBF模型模拟结果,甚至略高于GA-BP模型的预测精度,并且ELM模型具有参数选择简便、训练速度快、不会陷入局部最优值等特点,有着较大的计算优势。     

基于RF-LSTM的地表水体水质预测

水质预测是水污染防治的重要一环,为提高水质预测的精度,研究随机森林算法（RF）与长短时记忆神经网络（LSTM）相结合的预测方法。以桃林口水库水质监测数据为例,采用RF算法分别筛选出影响高锰酸盐指数（COD_Mn）、氨氮（NH₃—N）、总氮（TN）和总磷（TP）浓度变化的关键特征,在此基础上构建基于RF-LSTM的水质预测模型,并与单一LSTM、RF-BPNN和RF-RNN模型的预测效果进行对比。结果表明：RF-LSTM模型的预测效果均优于其他模型,预测COD_Mn、NH₃—N、TN和TP未来4 h浓度时的决定系数（R²）分别达到0.986、0.990、0.989和0.988,具有极高的预测精度和较强的泛化能力。研究结果为实现高精度水质预测提供了新思路。     

基于SUFI-2优化算法和SWAT模型的汾河流域月径流模拟

以黄河中游的汾河流域为研究区域,构建汾河流域SWAT分布式水文模型,采用SUFI-2优化算法进行参数敏感性分析、率定与不确定性分析,模拟了流域控制站河津水文站的月径流过程。结果表明:12个水文参数对径流的模拟均有不同程度的影响,对径流影响量最大的为土壤层有效含水量、其次为径流曲线数,影响最小的为主河道河床曼宁系数;率定期和验证期E_ns值均达到了0.80以上,相对误差R_e均小于20％,且确定性系数R²均大于0.85。汾河流域SWAT模型的月径流模拟效果较好,验证期较率定期落在不确定性区间的数量有所增加,表明验证期的径流模拟比率定期的径流模拟不确定性程度大。     

基于人工电场算法优化的大型灌区径流预测模型研究

针对水文预报中径流预测数据序列具有非线性和非平稳性等特点,将一种新型智能优化算法——人工电场算法AEFA与LSTM神经网络结合进行参数优化,建立AEFA-LSTM预测模型,并以赵口大型灌区涡河玄武水文站实测年径流量作为样本数据进行网络优化训练和预测分析,同时与传统优化算法（遗传算法GA和粒子群算法PSO）建立的GA-LSTM和PSO-LSTM预测模型进行对比。结果表明：AEFA-LSTM模型预测值的平均相对误差相较于GA-LSTM模型和PSO-LSTM模型分别降低了7.59%和5.22%,且平均绝对误差MAE、均方误差MSE、均方根误差RMSE均为3种模型中最小,说明所建立的AEFA-LSTM模型可以更高精度地预测径流量,为水文预报提供一种新型高精度径流预测方法。     

Estimation of Daily Pan Evaporation Using Two Different Adaptive Neuro-Fuzzy Computing Techniques

This paper investigates the ability of two different adaptive neuro-fuzzy inference systems (ANFIS) including grid partitioning (GP) and subtractive clustering (SC), in modeling daily pan evaporation (E_pan). The daily climatic variables, air temperature, wind speed, solar radiation and relative humidity of two automated weather stations, San Francisco and San Diego, in California State are used for pan evaporation estimation. The results of ANFIS-GP and ANFIS-SC models are compared with multivariate non-linear regression (MNLR), artificial neural network (ANN), Stephens-Stewart (SS) and Penman models. Determination coefficient (R²), root mean square error (RMSE) and mean absolute relative error (MARE) are used to evaluate the performance of the applied models. Comparison of results indicates that both ANFIS-GP and ANFIS-SC are superior to the MNLR, ANN, SS and Penman in modeling E_pan. The results also show that the difference between the performances of ANFIS-GP and ANFIS-SC is not significant in evaporation estimation. It is found that two different ANFIS models could be employed successfully in modeling evaporation from available climatic data.     

Utilizing RBF-NN and ANFIS Methods for Multi-Lead ahead Prediction Model of Evaporation from Reservoir

Evaporation as a major meteorological component of the hydrologic cycle plays a key role in water resources studies and climate change. The estimation of evaporation is a complex and unsteady process, so it is difficult to derive an accurate physical-based formula to represent all parameters that effect on estimate evaporation. Artificial intelligence-based methods may provide reliable prediction models for several applications in engineering. In this research have been introduced twelve networks with the RBF-NN and ANFIS methods. These models have applied to prediction daily evaporation at Layang reservoir, located in the southeast part of Malaysia. The used meteorological data set to develop the models for prediction daily evaporation rate from water surface for Layang reservoir includes daily air temperature, solar radiation, pan evaporation, and relative humidity that measured at a case study for fourteen years. The obtained result denote to the superiority of the RBF-NN models on the ANFIS models. A comparison of the model performance between RBF-NN and ANFIS models indicated that RBF-NN method presents the best estimates of daily evaporation rate with the minimum MSE 0.0471 , MAE 0.0032, RE and maximum R² 0.963.     

Regional-Specific Numerical Models of Evapotranspiration Using Gene-Expression Programming Interface in Sahel

An accurate and simple Reference Evapotranspiration (ETo) numerical model eases to use for supporting irrigation planning and its effective management is highly desired in Sahelian regions. This paper investigates the performance ability of the Gene-expression Programming (GEP) for modeling ETo using decadal climatic data from a Sahelian country; Burkina Faso. For the study; important data are collected from six synoptic meteorological stations located in different regions; Gaoua, P?, Boromo, Ouahigouya, Bogandé and Dori. The climatic data combinations are used as inputs to develop the GEP models at regional-specific data basis for estimating ETo. GEP performances are evaluated with the root mean square error (RMSE), and coefficient of correlation (R) between estimated and targeted Penman-Monteith FAO56 set as the true reference values. Obviously; from the statistical viewpoint; GEP computing technique has showed a good ability for providing numerical models on a regional data basis. The performances of GEP based on temperatures data are quite good able to substitute empirical equations at regional level to some extent. It is found that the models with wind velocity yield high accuracies by causing radical improve of the performances with R² (0.925-0.961) and RMSE (0.131-0.272?mm?day^-1); while relative humidity may cause only (R²?=?0.801-0.933 and RMSE?=?0.370-0.578?mm?day^-1). Statistically; GEP is an effectual modeling tool for computing successfully evapotranspiration in Sahel.     

Estimation of Suspended Sediment Yield in Natural Rivers Using Machine-coded Linear Genetic Programming

Estimation of suspended sediment yield is subject to uncertainty and bias. Many methods have been developed for estimating sediment yield but they still lack accuracy and robustness. This paper investigates the use of a machine-coded linear genetic programming (LGP) in daily suspended sediment estimation. The accuracy of LGP is compared with those of the Gene-expression programming (GEP), which is another branch of GP, and artificial neural network (ANN) technique. Daily streamflow and suspended sediment data from two stations on the Tongue River in Montana, USA, are used as case studies. Root mean square error (RMSE) and determination coefficient (R²) statistics are used for evaluating the accuracy of the models. Based on the comparison of the results, it is found that the LGP performs better than the GEP and ANN techniques. The GEP was also found to be better than the ANN. For the upstream and downstream stations, it is found that the LGP models with RMSE = 175 ton/day, R² = 0.941 and RMSE = 254 ton/day, R² = 0.959 in test period is superior in estimating daily suspended sediments than the best accurate GEP model with RMSE = 231 ton/day, R² = 0.941 and RMSE = 331 ton/day, R² = 0.934, respectively.     

A Comparison Between Conventional and M5 Model Tree Methods for Converting Pan Evaporation to Reference Evapotranspiration for Semi-Arid Region

In this study, the performance of M5 model tree and conventional method for converting pan evaporation data (E_p) to reference evapotranspiration (ET₀) were assessed in semi-arid regions. Conventional method uses pan coefficient (K_p) as a factor to convert E_p to ET₀. Two common K_p equations for pans with dry fetch (Allen et al. 1998; Abdel-Wahed and Snyder in J Irrig Drain Eng 134(4):425–429, 2008) were considered for the comparison. The values of ET₀ derived using these three methods were compared to those estimated using the reference FAO Penmane Monteith (FAO-PM) method under semi-arid conditions of the Khuzestan plain (Southwest Iran). The results showed that the M5 model is the best one to estimate ET₀ over test sites (0.5 mm d^?1 of root mean square error (RMSE) and 0.98 of coefficient of determination (R ²). Conversely, the performance of the two K_p equations was poor.     

Estimating Pan Evaporation from Limited Meteorological Observations from Turkey

ABSTRACT

Pan evaporation measurements are widely used to estimate evapotranspiration and free water evaporation. Pan evaporation measurements are critical to many applications including irrigation system design, irrigation scheduling, and hydrologic modeling. In many locations, reliable climate measurements consist of daily minimum screen temperature, daily maximum, rainfall, and windspeed. In many situations, it is advantageous to calculate rather than measure pan evaporation. Many formulas have been developed which predict pan evaporation as a function of limited meteorological observations. One of them, a simplified version of Penman's evaporation formula, requires only temperature, wind and dewpoint data in addition to latitude and elevation. This paper evaluates the Penpan Equation for the case of a pan and tests its universality. Estimates differ from measured values by about 0.65 mm/day at 19 locations in Turkey.     

Rainfall Pattern Forecasting Using Novel Hybrid Intelligent Model Based ANFIS-FFA

In this study, a new hybrid model integrated adaptive neuro fuzzy inference system with Firefly Optimization algorithm (ANFIS-FFA), is proposed for forecasting monthly rainfall with one-month lead time. The proposed ANFIS-FFA model is compared with standard ANFIS model, achieved using predictor-predictand data from the Pahang river catchment located in the Malaysian Peninsular. To develop the predictive models, a total of fifteen years of data were selected, split into nine years for training and six years for testing the accuracy of the proposed ANFIS-FFA model. To attain optimal models, several input combinations of antecedents’ rainfall data were used as predictor variables with sixteen different model combination considered for rainfall prediction. The performances of ANFIS-FFA models were evaluated using five statistical indices: the coefficient of determination (R ² ), Nash-Sutcliffe efficiency (NSE), Willmott’s Index (WI), root mean square error (RMSE) and mean absolute error (MAE). The results attained show that, the ANFIS-FFA model performed better than the standard ANFIS model, with high values of R ² , NSE and WI and low values of RMSE and MAE. In test phase, the monthly rainfall predictions using ANFIS-FFA yielded R ² , NSE and WI of about 0.999, 0.998 and 0.999, respectively, while the RMSE and MAE values were found to be about 0.272 mm and 0.133 mm, respectively. It was also evident that the performances of the ANFIS-FFA and ANFIS models were very much governed by the input data size where the ANFIS-FFA model resulted in an increase in the value of R ² , NSE and WI from 0.463, 0.207 and 0.548, using only one antecedent month of data as an input (t-1), to almost 0.999, 0.998 and 0.999, respectively, using five antecedent months of predictor data (t-1, t-2, t-3, t-6, t-12, t-24). We ascertain that the ANFIS-FFA is a prudent modelling approach that could be adopted for the simulation of monthly rainfall in the present study region.     

Gene-Expression Programming for Short-Term Forecasting of Daily Reference Evapotranspiration Using Public Weather Forecast Information

This study aimed to forecast the daily reference evapotranspiration (ETo) using a gene-expression programming (GEP) algorithm with limited public weather forecast information over Gaoyou station, located in Jiangsu province, China. To calibrate and validate the gene-expression code, important meteorological data and weather forecast information were collected from the local meteorological station and public weather media, respectively. The GEP algebraic formulation was successfully constructed based only on daily minimum and maximum air temperature using the true FAO56 Penman-Monteith (PM) set as reference values. The performance of the models was then assessed using the correlation coefficient (R), root mean squared error (RMSE), root relative squared error (RRSE) and mean absolute error (MAE). The study demonstrated that GEP is able to calibrate ETo (all errors ≤0.990 mm/day, R = 0.832–0.866) and forecast the daily ETo with good accuracy (RMSE = 1.207 mm/day, MAE = 0.902 mm/day, RRSE = 0.629 mm/day, R = 0.777). The model accuracies slightly decreased over a 7-day forecast lead-time. These results suggest that the GEP algorithm can be considered as a deployable tool for ETo forecast to anticipate decision on short-term irrigation schedule in the study zone.     

Changes of Pan Evaporation in the Recent 40 Years in the Yellow River Basin

Abstract

Based on monitoring data of 123 meteorological stations from 1960 to 2000 near or in the Yellow River Basin, the spatial and temporal distributions and their trends for pan evaporation (PE) are investigated in this study. The results indicate that, despite the annual mean air temperature over the Yellow River Basin has, on average, increased by 0.6° over the past 40 years, the rate of PE has steadily decreased, especially in summer and spring. Compared with the period of 1960s to 1970s, the rate of annual pan evaporation during 1980s to 1990s has decreased by 126mm or 7.0 percent. Spatial distribution of the rate of change show that this kind of trend is general but not universal, PE has significantly decreased over the upper and lower reaches of the Yellow River, but increased to a small degree over the middle reaches. Further analyses show that the decrease of PE is mainly related to reductions in sunshine durations and solar irradiance, owing to more clouds and aerosols.     

Performance of Different Surface Incoming Solar Radiation Models and Their Impacts on Reference Evapotranspiration

Reference evapotranspiration (ET₀) from FAO-Penman-Monteith equation is highly sensitive to the surface incoming solar radiation (SISR) and therefore accurate estimate of this parameter would result in more accurate estimation of ET₀. In this study, the accuracy of three main approaches for SISR estimation including empirical models (Angstrom and Hargreaves-Samani), physically-based data assimilation models (Global Land Data Assimilation System-Noah, GLDAS/Noah, and National Centers of Environmental Predictions/National Center for Atmospheric Research, NCEP/NCAR), and a satellite observation model (Satellite Application Facility on Climate Monitoring, CM-SAF) were evaluated using ground-based measurements from 2012 to 2015. Then SISR outputs from introduced approaches were implemented in FAO-Penman-Monteith equation for ET₀ estimation on daily and monthly basis. The Angstrom calibrated model was the most accurate model with a coefficient of determination (R²) of 0.9 and standard error of estimate (SEE) of 2.58 MJ. m^?2. d^?1, and GLDAS/Noah, Hargreaves-Samani, NCEP/NCAR, and CM-SAF, had lower accuracy, respectively. However, the lack of the meteorological data and required empirical coefficients are the main limitations of applying the empirical models, however, satellite-based approaches are more practical for operational purposes. The results indicated that, in spite of slight overestimation in warm months, GLDAS/Noah model had better performance with R²=0.87 and SEE?=?3.5 MJ. m^?2. d^?1 in case of lack of meteorological data. The accuracy of ET₀ derived from FAO-Penman-Monteith equation was directly depended on the accuracy of SISR estimation. The ET₀ estimation error was related to SISR estimation error with a fourth-degree function and had a linear relationship with SISR error at daily and monthly scales, respectively.