Soil temperature modeling at different depths using neuro-fuzzy,neural network,and genetic programming techniques

The applicability of artificial neural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS), and genetic programming (GP) techniques in estimating soil temperatures (ST) at different depths is investigated in this study. Weather data from two stations, Mersin and Adana, Turkey, were used as inputs to the applied models in order to model monthly STs. The first part of the study focused on comparison of ANN, ANFIS, and GP models in modeling ST of two stations at the depths of 10, 50, and 100 cm. GP was found to perform better than the ANN and ANFIS-SC in estimating monthly ST. The effect of periodicity (month of the year) on models’ accuracy was also investigated. Including periodicity component in models’ inputs considerably increased their accuracies. The root mean square error (RMSE) of ANN models was respectively decreased by 34 and 27 % for the depths of 10 and 100 cm adding the periodicity input. In the second part of the study, the accuracies of the ANN, ANFIS, and GP models were compared in estimating ST of Mersin Station using the climatic data of Adana Station. The ANN models generally performed better than the ANFIS-SC and GP in modeling ST of Mersin Station without local climatic inputs.     

Comparison of artificial neural network and multivariate linear regression methods for estimation of daily soil temperature in an arid region

Soil temperature (T _S) strongly influences a wide range of biotic and abiotic processes. As an alternative to direct measurement, indirect determination of T _S from meteorological parameters has been the focus of attention of environmental researchers. The main purpose of this study was to estimate daily T _S at six depths (5, 10, 20, 30, 50 and 100?cm) by using a multilayer perceptron (MLP) artificial neural network (ANN) model and a multivariate linear regression (MLR) method in an arid region of Iran. Mean daily meteorological parameters including air temperature (T _a), solar radiation (R _S), relative humidity (RH) and precipitation (P) were used as input data to the ANN and MLR models. The model results of the MLR model were compared to those of ANN. The accuracy of the predictions was evaluated by the correlation coefficient (r), the root mean-square error (RMSE) and the mean absolute error (MAE) between the measured and predicted T _S values. The results showed that the ANN method forecasts were superior to the corresponding values obtained by the MLR model. The regression analysis indicated that T _a, RH, R _S and P were reasonably correlated with T _S at various depths, but the most effective parameters influencing T _S at different depths were T _a and RH.     

Hourly air temperature driven using multi-layer perceptron and radial basis function networks in arid and semi-arid regions

This study employed two artificial neural network (ANN) models, including multi-layer perceptron (MLP) and radial basis function (RBF), as data-driven methods of hourly air temperature at three meteorological stations in Fars province, Iran. MLP was optimized using the Levenberg–Marquardt (MLP_LM) training algorithm with a tangent sigmoid transfer function. Both time series (TS) and randomized (RZ) data were used for training and testing of ANNs. Daily maximum and minimum air temperatures (MM) and antecedent daily maximum and minimum air temperatures (AMM) constituted the input for ANNs. The ANN models were evaluated using the root mean square error (RMSE), the coefficient of determination (R ²) and the mean absolute error. The use of AMM led to a more accurate estimation of hourly temperature compared with the use of MM. The MLP-ANN seemed to have a higher estimation efficiency than the RBF ANN. Furthermore, the ANN testing using randomized data showed more accurate estimation. The RMSE values for MLP with RZ data using daily maximum and minimum air temperatures for testing phase were equal to 1.2°C, 1.8°C, and 1.7°C, respectively, at Arsanjan, Bajgah, and Kooshkak stations. The results of this study showed that hourly air temperature driven using ANNs (proposed models) had less error than the empirical equation.     

利用人工神经网络模型预测西北太平洋热带气旋生成频数

通过对60年(1950~2009年)北半球夏、秋季(6~10月)热带气旋(TC)频数与春季(3~5月)大尺度环境变量的相关分析,挑选出8个相关性较高的前期预报因子建立人工神经网络(ANN)模型,对2010~2017年8年夏、秋季TC频数进行回报,并将回报结果与传统多元线性回归(MLR)方法所得结果进行对比分析。结果表明,ANN模型对60年历史数据的拟合精度高,相关系数高达0.99,平均绝对误差低至0.77。在8年回报中,ANN模型相关系数为0.80,平均绝对误差为1.97;而MLR模型相关系数仅为0.46,平均绝对误差为3.30。ANN模型在历史数据拟合和回报中的表现都明显优于MLR模型,未来可考虑应用于实际的业务预测中。     

Estimation of ground temperatures in permafrost regions of the Qinghai-Tibetan Plateau from climatic variables

Ground temperature is an important factor influencing ground source heat pumps, ground energy storage systems, land-atmosphere processes, and ecosystem dynamics. This paper presents an accurate development model (DM) based on a segment function: it can derive ground temperatures in permafrost regions of the Qinghai-Tibetan Plateau (QTP) from air temperature in case of shallow soil depths and without using air temperature data in case of deep soil depths. Here, we applied this model to simulate the active layer and permafrost ground temperature at the Tanggula observation station. The DM results were compared with those from the artificial neural network (ANN), support vector machine (SVM), and multiple linear regressions (MLR) models, which were based on climatic variables from prior models and on ground temperatures derived from observations at different depths. The results revealed that the effect of air temperature on simulated ground temperatures decreased with increasing depth; moreover, ground temperatures fluctuated greatly within the shallow layers but remained rather stable with deeper layers. The results also indicated that the DM has the best performance for the estimation of soil temperature compared to the MLR, SVM, and ANN models. Finally, we obtained the three average statistics indexes, i.e., mean absolute error (MAE), root mean square error (RMSE), and the normalized standard error (NSEE) at TGL site: they were equal to 0.51 °C, 0.63 °C, and 0.15 °C for the ground temperature of active layer and to 0.08 °C, 0.09 °C, and 0.07 °C for the permafrost temperature.     

Utilization of PSO algorithm in estimation of water level change of Lake Beysehir

In this study, unlike backpropagation algorithm which gets local best solutions, the usefulness of particle swarm optimization (PSO) algorithm, a population-based optimization technique with a global search feature, inspired by the behavior of bird flocks, in determination of parameters of support vector machines (SVM) and adaptive network-based fuzzy inference system (ANFIS) methods was investigated. For this purpose, the performances of hybrid PSO-ε support vector regression (PSO-εSVR) and PSO-ANFIS models were studied to estimate water level change of Lake Beysehir in Turkey. The change in water level was also estimated using generalized regression neural network (GRNN) method, an iterative training procedure. Root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R ²) were used to compare the obtained results. Efforts were made to estimate water level change (L) using different input combinations of monthly inflow-lost flow (I), precipitation (P), evaporation (E), and outflow (O). According to the obtained results, the other methods except PSO-ANN generally showed significantly similar performances to each other. PSO-εSVR method with the values of minMAE = 0.0052 m, maxMAE = 0.04 m, and medianMAE = 0.0198 m; minRMSE = 0.0070 m, maxRMSE = 0.0518 m, and medianRMSE = 0.0241 m; minR ² = 0.9169, maxR ² = 0.9995, medianR ² = 0.9909 for the I-P-E-O combination in testing period became superior in forecasting water level change of Lake Beysehir than the other methods. PSO-ANN models were the least successful models in all combinations.     

Application of random forest time series,support vector regression and multivariate adaptive regression splines models in prediction of snowfall (a case study of Alvand in the middle Zagros,Iran)

We have conducted a case study to investigate the performance of support vector machine, multivariate adaptive regression splines, and random forest time series methods in snowfall modeling. These models were applied to a data set of monthly snowfall collected during six cold months at Hamadan Airport sample station located in the Zagros Mountain Range in Iran. We considered monthly data of snowfall from 1981 to 2008 during the period from October/November to April/May as the training set and the data from 2009 to 2015 as the testing set. The root mean square errors (RMSE), mean absolute errors (MAE), determination coefficient (R ²), coefficient of efficiency (E%), and intra-class correlation coefficient (ICC) statistics were used as evaluation criteria. Our results indicated that the random forest time series model outperformed the support vector machine and multivariate adaptive regression splines models in predicting monthly snowfall in terms of several criteria. The RMSE, MAE, R ², E, and ICC for the testing set were 7.84, 5.52, 0.92, 0.89, and 0.93, respectively. The overall results indicated that the random forest time series model could be successfully used to estimate monthly snowfall values. Moreover, the support vector machine model showed substantial performance as well, suggesting it may also be applied to forecast snowfall in this area.     

Estimating net radiation at surface using artificial neural networks: a new approach

This study describes the results of artificial neural network (ANN) models to estimate net radiation (R _n), at surface. Three ANN models were developed based on meteorological data such as wind velocity and direction, surface and air temperature, relative humidity, and soil moisture and temperature. A comparison has been made between the R _n estimates provided by the neural models and two linear models (LM) that need solar incoming shortwave radiation measurements as input parameter. Both ANN and LM results were tested against in situ measured R _n. For the LM ones, the estimations showed a root mean square error (RMSE) between 34.10 and 39.48?W?m^?2 and correlation coefficient (R ²) between 0.96 and 0.97 considering both the developing and the testing phases of calculations. The estimates obtained by the ANN models showed RMSEs between 6.54 and 48.75?W?m^?2 and R ² between 0.92 and 0.98 considering both the training and the testing phases. The ANN estimates are shown to be similar or even better, in some cases, than those given by the LMs. According to the authors?? knowledge, the use of ANNs to estimate R _n has not been discussed earlier, and based on the results obtained, it represents a formidable potential tool for R _n prediction using commonly measured meteorological parameters.     

Comprehensive modeling of monthly mean soil temperature using multivariate adaptive regression splines and support vector machine

Soil temperature (T _s) and its thermal regime are the most important factors in plant growth, biological activities, and water movement in soil. Due to scarcity of the T _s data, estimation of soil temperature is an important issue in different fields of sciences. The main objective of the present study is to investigate the accuracy of multivariate adaptive regression splines (MARS) and support vector machine (SVM) methods for estimating the T _s. For this aim, the monthly mean data of the T _s (at depths of 5, 10, 50, and 100 cm) and meteorological parameters of 30 synoptic stations in Iran were utilized. To develop the MARS and SVM models, various combinations of minimum, maximum, and mean air temperatures (T _min, T _max, T); actual and maximum possible sunshine duration; sunshine duration ratio (n, N, n/N); actual, net, and extraterrestrial solar radiation data (R _s, R _n, R _a); precipitation (P); relative humidity (RH); wind speed at 2 m height (u ₂); and water vapor pressure (V_p) were used as input variables. Three error statistics including root-mean-square-error (RMSE), mean absolute error (MAE), and determination coefficient (R ²) were used to check the performance of MARS and SVM models. The results indicated that the MARS was superior to the SVM at different depths. In the test and validation phases, the most accurate estimations for the MARS were obtained at the depth of 10 cm for T _max, T _min, T inputs (RMSE = 0.71 °C, MAE = 0.54 °C, and R ² = 0.995) and for RH, V _p, P, and u ₂ inputs (RMSE = 0.80 °C, MAE = 0.61 °C, and R ² = 0.996), respectively.     

Estimation of dew point temperature using neuro-fuzzy and neural network techniques

This study investigates the ability of two different artificial neural network (ANN) models, generalized regression neural networks model (GRNNM) and Kohonen self-organizing feature maps neural networks model (KSOFM), and two different adaptive neural fuzzy inference system (ANFIS) models, ANFIS model with sub-clustering identification (ANFIS-SC) and ANFIS model with grid partitioning identification (ANFIS-GP), for estimating daily dew point temperature. The climatic data that consisted of 8 years of daily records of air temperature, sunshine hours, wind speed, saturation vapor pressure, relative humidity, and dew point temperature from three weather stations, Daego, Pohang, and Ulsan, in South Korea were used in the study. The estimates of ANN and ANFIS models were compared according to the three different statistics, root mean square errors, mean absolute errors, and determination coefficient. Comparison results revealed that the ANFIS-SC, ANFIS-GP, and GRNNM models showed almost the same accuracy and they performed better than the KSOFM model. Results also indicated that the sunshine hours, wind speed, and saturation vapor pressure have little effect on dew point temperature. It was found that the dew point temperature could be successfully estimated by using T _mean and R _H variables.     

Utility of coactive neuro-fuzzy inference system for pan evaporation modeling in comparison with multilayer perceptron

Estimation of pan evaporation (E _pan) using black-box models has received a great deal of attention in developing countries where measurements of E _pan are spatially and temporally limited. Multilayer perceptron (MLP) and coactive neuro-fuzzy inference system (CANFIS) models were used to predict daily E _pan for a semi-arid region of Iran. Six MLP and CANFIS models comprising various combinations of daily meteorological parameters were developed. The performances of the models were tested using correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE) and percentage error of estimate (PE). It was found that the MLP6 model with the Momentum learning algorithm and the Tanh activation function, which requires all input parameters, presented the most accurate E _pan predictions (r?=?0.97, RMSE?=?0.81?mm?day^?1, MAE?=?0.63?mm?day^?1 and PE?=?0.58?%). The results also showed that the most accurate E _pan predictions with a CANFIS model can be achieved with the Takagi–Sugeno–Kang (TSK) fuzzy model and the Gaussian membership function. Overall performances revealed that the MLP method was better suited than CANFIS method for modeling the E _pan process.     

Spatiotemporal modeling of monthly soil temperature using artificial neural networks

Soil temperature data are critical for understanding land–atmosphere interactions. However, in many cases, they are limited at both spatial and temporal scales. In the current study, an attempt was made to predict monthly mean soil temperature at a depth of 10 cm using artificial neural networks (ANNs) over a large region with complex terrain. Gridded independent variables, including latitude, longitude, elevation, topographic wetness index, and normalized difference vegetation index, were derived from a digital elevation model and remote sensing images with a resolution of 1 km. The good performance and robustness of the proposed ANNs were demonstrated by comparisons with multiple linear regressions. On average, the developed ANNs presented a relative improvement of about 44 % in root mean square error, 70 % in mean absolute percentage error, and 18 % in coefficient of determination over classical linear models. The proposed ANN models were then applied to predict soil temperatures at unsampled locations across the study area. Spatiotemporal variability of soil temperature was investigated based on the obtained database. Future work will be needed to test the applicability of ANNs for estimating soil temperature at finer scales.     

基于多种机器学习模型的西北地区蒸散发模拟与趋势分析

基于机器学习方法和多源数据构建高精度蒸散发（Evapotranspiration,ET）产品对研究气候变化背景下干旱、半干旱地区陆地水循环变化具有重要意义。本文利用西北地区12个草地通量站点与卫星遥感产品,基于随机森林、极端梯度提升、支持向量回归和人工神经网络4种机器学习方法构建ET估算模型,制作5 km分辨率ET产品,并分析ET的长期变化趋势。交叉验证结果表明,4种模型的均方根误差都低于0.57 mm·d^-1,R²高达0.73～0.88。SHAP （SHapley Additive exPlanation）可解释性分析表明,4种模型均将净辐射、植被和土壤湿度作为ET估算的重要因子,也能刻画出土壤偏干时土壤水分对ET的限制作用,有较好的物理解释性。多模型集合的ET结果相比单一机器学习模型以及现有遥感产品误差分别降低7％～20％和45％～70％。趋势分析结果显示,西北地区非裸地下垫面在2001—2018年间整体呈现ET增加趋势,平均速率为19 mm/（10 a）。在河套平原和内蒙古中部和东北部地区,ET的增长速率超过降水,这可能会进一步加剧这些地区的干旱化。     

Estimating sunshine duration from other climatic data by artificial neural network for ET0 estimation in an arid environment

Sunshine duration data are desirable for calculating daily solar radiation (R _s) and subsequent reference evapotranspiration (ET₀) using the Penman–Monteith (PM) method. In the absence of measured R _s data, the Ångström equation has been recommended by the Food and Agriculture Organization (FAO) of the United Nations. This equation requires actual sunshine duration that is not commonly observed at many weather stations. This paper examines the potential for the use of artificial neural networks (ANNs) to estimate sunshine duration based on air temperature and humidity data under arid environment. This is important because these data are commonly available parameters. The impact of the estimated sunshine duration on estimation of R _s and ET₀ was also conducted. The four weather stations selected for this study are located in Sistan and Baluchestan Province (southeast of Iran). The study demonstrated that modelling of sunshine duration through the use of ANN technique made acceptable estimates. Models were compared using the determination coefficient (R ²), the root mean square error (RMSE) and the mean bias error (MBE). Average R ², RMSE and MBE for the comparison between measured and estimated sunshine duration were calculated resulting 0.81, 6.3 % and 0.1 %, respectively. Our analyses also demonstrate that the difference between the measured and estimated sunshine duration has less effect on the estimated R _s and ET₀ by using Ångström and FAO-PM equations, respectively.     

Quantifying spatial patterns of bioclimatic zones and controls in Turkey

Summary The study was aimed at inferring spatial patterns of climatic zones as well as identifying significant discriminating bioclimatic controls for distribution of major ecosystems in Turkey, based on multivariate analyses. A total of 12 climate variables and 11 bioclimatic indices for the period of 1968–2004 at 272 meteorological stations, and four location data (latitudes, longitudes, altitudes, and distance to sea) were analyzed using discriminant analysis (DA), hierarchical and non-hierarchical cluster analyses (CA), principal components analysis (PCA), and multiple linear regression (MLR) models. The first three and four linear discriminant functions (LDFs) explained 88 and 95% of the variation in the dataset, respectively. The efficacy of the discriminant model was high (85.5%) based on the cross-validation method. The hierarchical and non-hierarchical CA pointed to seven clusters (climate types) that can be observed on the basis of broad climatic similarity of 97%. PCA elucidated 78% of variation in the dataset. MLR models that accounted for variations in the 12 climatic response variables as a function of the four location variables and aspect had R ² values ranging from 28.8% for precipitation to 89.8% for mean air temperature and soil temperature for a depth of 5 cm. The multivariate analyses indicated that the meteorological stations are heterogeneous clusters consisting of the seven climatic zones. However, differences in the bioclimatic variables at the boundaries complicate the natural clustering scheme of a multidimensional cloud of data points and were detected in a climatologically plausible manner by the Ward and K-means CA, and PCA. Our multivariate approach revealed that the commonly used climatic zones are insufficient representations of the inferred climatic zones: (1) the coastal Black Sea; (2) the inland Black Sea; (3) the southeastern Anatolia; (4) the eastern Anatolia; (5) the central Anatolia; (6) the Mediterranean; and (7) the Aegean. Authors’ addresses: F. Evrendilek, Department of Environmental Engineering, Faculty of Engineering and Architecture, Abant Izzet Baysal University, G?lk?y Cambus, 14280 Bolu, Turkey; S. Berberoglu, Department of Landscape Architecture, Cukurova University, Balcali-Adana, Turkey.     

EFFECTS OF A CLOUD FILTERING METHOD FOR FENGYUN-3C MICROWAVE HUMIDITY AND TEMPERATURE SOUNDER MEASUREMENTS OVER OCEAN ON RETRIEVALS OF TEMPERATURE AND HUMIDITY

For Microwave Humidity and Temperature sounder (MWHTS) measurements over the ocean, a cloud filtering method is presented to filter out cloud- and precipitation-affected observations by analyzing the sensitivity of the simulated brightness temperatures of MWHTS to cloud liquid water, and using the root mean square error (RMSE) between observation and simulation in clear sky as a reference standard. The atmospheric temperature and humidity profiles are retrieved using MWHTS measurements with and without filtering by multiple linear regression (MLR), artificial neural networks (ANN) and one- dimensional variational (1DVAR) retrieval methods, respectively, and the effects of the filtering method on the retrieval accuracies are analyzed. The numerical results show that the filtering method can improve the retrieval accuracies of the MLR and the 1DVAR retrieval methods, but have little influence on that of the ANN. In addition, the dependencies of the retrieval methods upon the testing samples of brightness temperature are studied, and the results show that the 1DVAR retrieval method has great stability due to that the testing samples have great impact on the retrieval accuracies of the MLR and the ANN, but have little impact on that of the 1DVAR.     

我国冬季持续低温事件预报模型的建立

利用1979—2010年我国冬季522个站点的日平均温度资料,使用基于尺度分离的多元线性回归方法建立预报模型,对我国冬季的持续低温事件的预报做了一定的尝试。将温度按照一定的方法进行尺度分离,分解出年际、月、季节内尺度温度,对各个部分分别进行拟合再相加。挑选特定海区的海温、北极海冰作为年际尺度温度预测因子,多个低频气象场作为季节内温度预测因子,利用1979—2003年资料拟合出各因子回归系数。用重构的冬季温度挑选出持续低温事件并与实际的事件进行对比检验,计算出此方法的TS评分为0.57,再利用2008年初我国南方大范围的持续低温事件检验拟合结果。检验结果表明基于时间尺度分离的多元线性回归方法在持续低温事件的预报中有一定的参考意义。     

Adaptive neuro-fuzzy inference system to forecast peak gust speed during thunderstorms

The aim of the present study is to develop an adaptive neuro-fuzzy inference system (ANFIS) to forecast the peak gust speed associated with thunderstorms during the pre-monsoon season (April?CMay) over Kolkata (22°32??N, 88°20??E), India. The pre-monsoon thunderstorms during 1997?C2008 are considered in this study to train the model. The input parameters are selected from various stability indices using statistical skill score analysis. The most useful and relevant stability indices are taken to form the input matrix of the model. The forecast through the hybrid ANFIS model is compared with non-hybrid radial basis function network (RBFN), multi layer perceptron (MLP) and multiple linear regression (MLR) models. The forecast error analyses of the models in the test cases reveal that ANFIS provides the best forecast of the peak gust speed with 3.52% error, whereas the errors with RBFN, MLP, and MLR models are 10.48, 11.57, and 12.51%, respectively. During the validation with the 2009 observations of the India Meteorological Department (IMD), the ANFIS model confirms its superiority over other comparative models. The forecast error during the validation of the ANFIS model is observed to be 3.69%, with a lead time of <12?h, whereas the errors with RBFN, MLP, and MLR are 12.25, 13.19, and 14.86%, respectively. The ANFIS model may, therefore, be used as an operational model for forecasting the peak gust speed associated with thunderstorms over Kolkata during the pre-monsoon season.     

Phenological observations made by the I. R. Bohemian Patriotic�CEconomic Society, 1828�C1847

Drought forecasting is a critical component of drought risk management. Identification of effective predictors is a major component of forecasting models. Sea surface temperature (SST) and sea level pressure (SLP) are relevant predictors for short- to long-term drought forecasts. However, these datasets are captured globally within a cell-wise network. This paper describes an approach to locate the most effective cells of the SST and SLP datasets using data mining. They are then applied as input to an adaptive neurofuzzy inference system (ANFIS) model to forecast possible droughts 3, 6, and 9?months in advance. Tehran plain was selected as the study area, and drought events are designated using the effective drought index (EDI). In another treatment, past values of the EDI time series were introduced to the ANFIS and the results compared with the previous findings. It was shown that R ² values were higher for all cases applying the SST/SLP datasets. Additionally, the performance of SST/SLP datasets and the ANFIS model was assessed according to ??drought?? or ??wet?? classification, and it was concluded that more than 90% of the time the ANFIS model detected the drought status correctly or with only a one class error.