首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 46 毫秒
1.
This paper examines the potential for the use of artificial neural networks (ANNs) to estimate the reference crop evapotranspiration (ET0) based on air temperature data under humid subtropical conditions on the southern coast of the Caspian Sea situated in the north of Iran. The input variables for the networks were the maximum and minimum air temperature and extraterrestrial radiation. The temperature data were obtained from eight meteorological stations with a range of latitude, longitude, and elevation throughout the study area. A comparison of the estimates provided by the ANNs and by Hargreaves equation was also conducted. The FAO-56 Penman–Monteith model was used as a reference model for assessing the performance of the two approaches. The results of this study showed that ANNs using air temperature data successfully estimated the daily ET0 and that the ANNs with an R 2 of 0.95 and a root mean square error (RMSE) of 0.41 mm day?1 simulated ET0 better than the Hargreaves equation, which had an R 2 of 0.91 and a RMSE of 0.51 mm day?1.  相似文献   

2.
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.  相似文献   

3.
Meteorological stations, which measure all the required meteorological parameters to estimate reference evapotranspiration (ETo) using the Food and Agriculture Organization Penman?CMonteith (FAO56-PM) method, are limited in Korea. In this study, alternative methods were applied to estimate these parameters, and the applicability of these methods for ETo estimation was evaluated by comparison with a complete meteorological dataset collected in 2008 in Korea. Despite differences between the estimation and observation of radiation and wind speed, the comparison of ETo showed small differences [i.e., mean bias error (MBE) varying ?0.22 to 0.25?mm?day?1 and root-mean-square-error (RMSE) varying 0.06?C0.50?mm?day?1]. The estimated vapor pressure differed considerably from the observed, resulting in a larger discrepancy in ETo (i.e., MBE of ?0.50?mm?day?1 and RMSE of 0.60?C0.73?mm?day?1). Estimated ETo showed different sensitivity to variations of the meteorological parameters??in order of vapor pressure?>?wind speed?>?radiation. It is clear that the FAO56-PM method is applicable for reasonable ETo estimation at a daily time scale especially in data-limited regions in Korea.  相似文献   

4.
Accurate estimation of reference evapotranspiration (ET0) becomes imperative for better managing the more and more limited agricultural water resources. This study examined the feasibility of developing generalized artificial neural network (GANN) models for ET0 estimation using weather data from four locations representing different climatic patterns. Four GANN models with different combinations of meteorological variables as inputs were examined. The developed models were directly tested with climatic data from other four distinct stations. The results showed that the GANN model with five inputs, maximum temperature, minimum temperature, relative humidity, solar radiation, and wind speed, performed the best, while that considering only maximum temperature and minimum temperature resulted in the lowest accuracy. All the GANN models exhibited high accuracy under both arid and humid conditions. The GANN models were also compared with multivariate linear regression (MLR) models and three conventional methods: Hargreaves, Priestley–Taylor, and Penman equations. All the GANN models showed better performance than the corresponding MLR models. Although Hargreaves and Priestley–Taylor equations performed slightly better than the GANN models considering the same inputs at arid and semiarid stations, they showed worse performance at humid and subhumid stations, and GANN models performed better on average. The results of this study demonstrated the great generalization potential of artificial neural techniques in ET0 modeling.  相似文献   

5.
The present study evaluates firstly the ability of the FAO-56 methodology, based on the two-step approach “reference evapotranspiration (ET0)—crop coefficient (K c),” to accurately determine the actual evapotranspiration (ET) of irrigated crops and proposes, secondly, the alternative approaches for improving this determination. The FAO-56 methodology is supported by two hypotheses: (1) ET0 represents all effects of weather and (2) K c varies predominately with specific crop characteristics and only marginally with climate, which enables the transfer of K c standard values among locations and climates. On the base of the theoretical analysis and experimental observations, a critical examination of the previous hypotheses demonstrates that they are not verified by reality. The first hypothesis is not verified for two reasons: (a) The formulation adapted by the Penman–Monteith equation and proposed in FAO-56 methodology for calculating ET0 uses climatic variables determined at a 24-h average scale. However, in principle it is only valid in permanent regime, in other words at least on an hourly scale. (b) The FAO-56-proposed formulation attributes a constant value to the canopy resistance of the reference surface; but in reality, this resistance is variable in relation to the climatic variables. The second hypothesis, concerning the two-step approach, is also not verified because the values of K c largely vary in relation to climatic variables (radiation, air vapour pressure deficit and wind speed). This fact does not support the possibility of the transferability of K c values into locations where the local conditions deviate from the conditions where the adjusted values of K c were determined. The weakness of the ET estimation, observed on several crops cultivated in the Mediterranean region, through the application of the FAO-56 methodology, is the result of errors accumulation, associated with that affects the determination of either ET0 or K c. The present study underlines the advantage of using a one-step approach in the calculation of ET, since it is based on fewer computation steps and, consequently, on fewer error sources than the two-step model. Two models adopting this approach are proposed and validated, one of which can be considered as operational, i.e. it only needs standard meteorological data as input. The use of these models enables an improvement of the ET estimation. This objective is a key component of any strategy to improve agricultural water management in Mediterranean region.  相似文献   

6.
Direct calculation of actual evapotranspiration ETc based on Penman-Monteith type models gives more accurate values than indirect models, which need the determination of reference evapotranspiration and crop coefficient. However, the direct models need the measurement of weather variables above the crop, which is limiting and not easily feasible in practice. An operational version of a known ETc direct model is described and tested. This new version is based on the determination of the weather variables collected in a standard agro-meteorological station. The original and the operational versions of the ETc model were validated on two crops with contrasting height: soybean (0.8 m) and sweet sorghum (3 m). For soybean, ETc calculated with the two versions gave results very similar at both hourly and daily scales. For sweet sorghum, ETc calculated with the operational version is good at daily scale and not as good, although acceptable, at the hourly scale.  相似文献   

7.
The FAO Penman–Monteith (F-PM) method is a frequently applied approach for calculating the daily reference evapotranspiration (ET0). This method requires long records of meteorological data, which makes it quite hard to employ in locations with no or limited available data. Evaporation pans are widely used to estimate the reference ET0, but this method requires reliable estimates of the pan coefficient (K p). The objectives of this study were to determine the proper values of monthly and annual K p, as well as the best method among those available for the estimation of K p values in the study area. Measured weather data from 1992 to 2006 were obtained from 18 stations in the North and Northwest of Iran. Daily ET0 calculated using methods by Bernardo et al. and Pereira et al. were compared with those calculated by the F-PM method. The employed methods at all stations, except those located in the north of the study area with high relative humidity, overestimated the ET0 compared to the F-PM method. The constant parameters of these methods were optimized by a trial and error scheme to minimize the root mean square error. The results indicated that modified K p coefficients from Bernardo et al.’s method ranged between 0.41 and 0.87 and the optimal coefficient of Pereira et al.’s method ranged between 0.49 and 0.95. Modified monthly K p from Bernardo et al.’s method ranged between 0.3 and 1.07 and those from Pereira et al.’s method ranged between 0.4 and 1.18. Modified K p of the methods by Bernardo et al. and Pereira et al. showed the higher estimation accuracy of daily ET0 values. In general, the performance of the modified K p of Bernardo et al.’s method was higher than Pereira et al.’s method for all stations. Thus, in the study region and under the same climatic conditions [in areas with only pan evaporation (E p) records], the use of climatic monthly modified K p to calculate ET0 based on class A E p is recommended.  相似文献   

8.
Global warming has caused unevenly distributed changes in precipitation and evapotranspiration, which has and will certainly impact on the wet-dry variations. Based on daily meteorological data collected at 91 weather stations in Northeast China (NEC), the spatiotemporal characteristics of dry and wet climatic variables (precipitation, crop reference evapotranspiration (ET0), and humid index (HI)) are analyzed, and the probable reasons causing the changes in these variables are discussed during the period of 1961–2014. Precipitation showed non-significant trend over the period of 1961–2014, while ET0 showed a significant decreasing trend, which led to climate wetting in NEC. The period of 2001–2012 exhibited smaller semiarid area and larger humid area compared to the period of 1961–1980, indicating NEC has experienced wetting process at decadal scale. ET0 was most sensitive to relative humidity, and wind speed was the second most sensitive variable. Sunshine hours and temperature were found to be less influential to ET0 in the study area. The changes in wind speed in the recent 54 years have caused the greatest influence on ET0, followed by temperature. For each month, wind speed was the most significant variable causing ET0 reduction in all months except July. Temperature, as a dominant factor, made a positive contribution to ET0 in February and March, as well as sunshine hours in June and July, and relative humidity in August and September. In summary, NEC has experienced noticeable climate wetting due to the significantly decreasing ET0, and the decrease in wind speed was the biggest contributor for the ET0 reduction. Although agricultural drought crisis is expected to be partly alleviated, regional water resources management and planning in Northeast China should consider the potential water shortage and water conflict in the future because of spatiotemporal dry-wet variations in NEC.  相似文献   

9.
The monthly rainfall data from 1901 to 2011 and maximum and minimum temperature data from 1901 to 2005 are used along with the reference evapotranspiration (ET0) to analyze the climate trend of 45 stations of Madhya Pradesh. ET0 is calculated by the Hargreaves method from 1901 to 2005 and the computed data is then used for trend analysis. The temporal variation and the spatial distribution of trend are studied for seasonal and annual series with the Mann-Kendall (MK) test and Sen’s estimator of slope. The percentage of change is used to find the rate of change in 111 years (rainfall) and 105 years (temperatures and ET0). Interrelationships among these variables are analyzed to see the dependency of one variable on the other. The results indicate a decreasing rainfall and increasing temperatures and ET0 trend. A similar pattern is noticeable in all seasons except for monsoon season in temperature and ET0 trend analysis. The highest increase of temperature is noticed during post-monsoon and winter. Rainfall shows a notable decrease in the monsoon season. The entire state of Madhya Pradesh is considered as a single unit, and the calculation of overall net change in the amount of the rainfall, temperatures (maximum and minimum) and ET0 is done to estimate the total loss or gain in monthly, seasonal and annual series. The results show net loss or deficit in the amount of rainfall and the net gain or excess in the temperature and ET0 amount.  相似文献   

10.
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.  相似文献   

11.
Reference evapotranspiration (ETo) is significant for water resources planning and environmental studies. Many equations have been developed for ETo estimation in various geographic and climatic conditions, of which, the Penman–Monteith FAO 56 (PMF-56) equation was accepted as reference method. A major complication in estimating ETo by the PMF-56 model is the requirement for meteorological data that may not be readily available from typical weather stations in many areas of the globe. This restriction necessitates use of simpler models which require less input data. In this study, the original and five modified versions of the Hargreaves equation that require only temperature and rainfall were evaluated in humid, semi-humid, semi-arid and arid climates in Iran. The results showed that the original and modified versions of the Hargreaves equation had the poorest performance in semi-humid climate and the best performance in windy humid environment. Further, the ETo estimations with the Hargreaves equations having rainfall parameter were poor as compared to those from the PMF-56 method under majority of the climatic situations studied.  相似文献   

12.
This study investigated the spatial–temporal patterns and trends of potential evapotranspiration (ET0) and aridity index (AI) over Southwest China during 1960–2013 based on daily temperature, precipitation, wind speed, sunshine duration, total solar radiation, and relative humidity data from 108 meteorological stations. The Penman–Monteith model, Mann–Kendall (M–K) test, moving t test, and Morlet wavelet method were used. The results indicated that ET0 and AI across the region displayed decreasing trends, but the former was significant. After 2000, regionally average trends in ET0 and AI increased rapidly, indicating that droughts increased over Southwest China in recent years. Spatially, the changes of ET0 and AI were dissimilar and not clustered, either. Temporally, both ET0 and AI displayed obvious abrupt change points over different timescales and that of AI was during the winter monsoon period. Significant periodic variations with periods of 27, 13, and 5 years were found in ET0, but only of 13 and 5 years existed in AI. Correlation analysis revealed that the sunshine duration and wind speed were the dominant factors affecting ET0 and that AI showed strong negative correlation with precipitation. The findings of this study enhance the understanding of the relationship between climate change and drought in Southwest China, while the mechanism controlling the variation in drought requires further study.  相似文献   

13.
Accurate estimation of reference evapotranspiration (ET 0 ) is essential for the computation of crop water requirements, irrigation scheduling, and water resources management. In this context, having a battery of alternative local calibrated ET 0 estimation methods is of great interest for any irrigation advisory service. The development of irrigation advisory services will be a major breakthrough for West African agriculture. In the case of many West African countries, the high number of meteorological inputs required by the Penman-Monteith equation has been indicated as constraining. The present paper investigates for the first time in Ghana, the estimation ability of artificial intelligence-based models (Artificial Neural Networks (ANNs) and Gene Expression Programing (GEPs)), and ancillary/external approaches for modeling reference evapotranspiration (ET 0 ) using limited weather data. According to the results of this study, GEPs have emerged as a very interesting alternative for ET 0 estimation at all the locations of Ghana which have been evaluated in this study under different scenarios of meteorological data availability. The adoption of ancillary/external approaches has been also successful, moreover in the southern locations. The interesting results obtained in this study using GEPs and some ancillary approaches could be a reference for future studies about ET 0 estimation in West Africa.  相似文献   

14.
利用区域气候模式RIEMS产品分析日蒸散量及其影响   总被引：1，自引：0，他引：1  
利用区域气候模式RIEMS输出的各种气象参数,采用了BEF等4种不同方法计算了沂沭河上游流域的潜在蒸散量,并与该流域6个气象站实测蒸发数据计算的陆面潜在蒸散量进行了比较。结果表明,根据平均偏差、平均绝对偏差、均方根差和相关系数指标的综合判断,该4种方法的估测精度从高到低依次为双线性曲面回归经验函数法(BEF)、Hargreaves-Samani(Harg)法、Pristley-Tayler(P-T)法和Penman-Monteith(P-M)法。在时间序列上,4种方法计算的逐日蒸散量与观测值呈相同的变化趋势,但计算值在蒸散发最强、最弱和降水最多、气温最高的7-9月有较大差异。BEF法估测的精度最高,与观测值最接近,Harg法、P-M法和P-T法都有明显的偏高现象。BEF法只需要较少的参数就能得到较高的估测精度,因此可作为利用区域气候模式RIEMS产品计算沂沭河流域蒸散量的首选方法,进而为RIEMS模式中耦合的陆面水文过程模型TOPX提供满足精度要求的日蒸散量驱动参数。  相似文献   

15.
Evapotranspiration and canopy resistance of grass in a Mediterranean region   总被引：1，自引：3，他引：1  
Summary A simple method for estimating actual evapotranspiration (ET) could become a suitable tool for irrigation scheduling. Resistance models can be useful if data on canopy resistance to water vapor flow (rc) and on aerodynamic resistance (ra) are available. These parameters are complex and hard to obtain. In this studyrc is analysed for a reference crop (grass meadow). Canopy resistance is dependent on climate, weather (radiation, atmospheric vapor pressure deficit, aerodynamic resistance), agronomic practices (irrigation, grass cutting) and time scale (hour, day). Anrc model, proposed by Katerji and Perrier (KP model), using some meteorological parameters as inputs, is presented. Canopy resistance calculated according to the KP model was used to estimate a referenceET ref on hourly and daily time scales.TheET ref estimated using the KP model on a daily time scale was compared with a model proposed by Allen, Jensen, Wright and Burman (AJWB model) — in whichrc depends on leaf area index only — and with direct measurements from a weighing lysimeter. The results show an underestimation of 18% for the AJWB model against an underestimation of 2% for the KP model. Since the hypotheses are the same for both models and aerodynamic resistance plays a secondary role, the better results obtained by the KP model are due torc modelling.With 11 Figures  相似文献   

16.
Reference crop evapotranspiration (ET0) is one of the most important climatic parameters which plays a key role in estimating crop water demand and scheduling irrigation. Under global warming and climate change conditions, it is needed to survey the trend of ET0 in Iran. In this study, ET0 values were determined based on FAO-56 Penman-Monteith equation over 32 synoptic meteorological stations during 1960–2005; and analyzed spatially and temporally in monthly, seasonal and annual time scales. After removing the significant lag-1 serial correlation effect by pre-whitening, non-parametric statistical Mann–Kendall (MK) test was used to detect the trends. The slope of the changes was determined by Sen’s slope estimator. In order to facilitate in trend analysis, the 10 moving average low pass filter were also applied on the normalized annual ET0 time series. Annual ET0 time series and filtered ones were then classified by hierarchical clustering in three clusters and then mapped in order to show the patterns of different clusters. Results showed that the significant decreasing trends were more considerable than increasing ones. Among surveyed stations, and on an annual time scale, the highest and lowest annual values of Sen’s slope estimator were observed in Tabas with (+) 72.14 mm per decade and Shahrud with (?) 62.22 mm per decade, respectively. Results also indicated that the clustered map based on normalized and filtered annual ET0 time series is in accordance with another map which showed spatial distribution of increasing, decreasing and non-significant trends of ET0 on annually time scale. Exploratory and visual analysis of smoothed time series showed increasing trend in recent years especially after 1980 and 1995. In brief, the upward trend of ET0 in recent years is a crucial issue with regard to the high cost of dam construction for agricultural aims in arid and semi-arid regions e.g. Iran.  相似文献   

17.
The study compares two formulas for calculating the daily evapotranspiration ET0 for a reference crop. The first formula was proposed by Allen et al. (AL), while the second one was proposed by Katerji and Perrier with the addition of the carbon dioxide (CO2) effect on evapotranspiration (KP). The study analyses the impact of the calculation by the two formulas on the irrigation requirement (IR). Both formulas are based on the Penman-Monteith equation but adopt different approaches for parameterising the canopy resistance r c . In the AL formula, r c is assumed constant and not sensitive to climate change, whereas in the KP formula, r c is first parameterised as a function of climatic variables, then ET0 is corrected for the air CO2 concentration. The two formulas were compared in two periods. The first period involves data from two sites in the Mediterranean region within a measured climate change period (1981–2006) when all the input climatic variables were measured. The second period (2070–2100) involves data from a future climate change period at one site when the input climatic variables were forecasted for two future climate scenarios (A2 and B2). The annual cumulated values of ET0 calculated by the AL formula are systematically lower than those determined by the KP formula. The differences between the ET0 estimation with the AL and KP formulas have a strong impact on the determination of the IR for the reference crop. In fact, for the two periods, the annual values of IR when ET0 is calculated by the AL formula are systematically lower than those calculated by the KP formula. For the actual measured climate change period, this reduction varied from 26 to 28 %, while for the future climate change period, it varied based on the scenario from 16 % (A2) to 20 % (B2).  相似文献   

18.
Variations of global evapotranspiration (ET) and fresh water discharge from land to oceans (D) are important components of global climate change, but have not been well monitored. In this study, we present an estimate of twenty years (1989 to 2008) variations of global D and ET derived from satellite remote-sensed measurements and recent reanalysis products, ERA-Interim and CFSR, by using a novel application of the water balance equations separately over land and over oceans. Time series of annual mean global D and ET from both satellite observations and reanalyses show clear positive and negative trends, respectively, as a result of modest increase of oceanic evaporation (E o ). The inter-annual variations of D are similar to the in-situ-based observations, and the negative trend of ET supports the previous result that relative humidity has decreased while temperature has increased on land. The results suggest considerable sensitivity of the terrestrial hydrological cycles (e.g., D and ET) to small changes in precipitation and oceanic evaporation.  相似文献   

19.
Lu  Xianghui  Zhang  Haina  Han  Yixiu  Bai  Hua  Li  Erhui 《Theoretical and Applied Climatology》2022,147(1-2):73-86

To achieve accurate evaluation of evapotranspiration of reference crops (ET0) in Jiangxi, China, in the absence of systematic climatological data, with reference to the FAO-56 Penman–Monteith (P-M) equation, the Priestley-Taylor (P–T) method, the Makkink method, the Hargreaves-Samani (H–S) method, the Irmak-Allen (I-A) method, the Penman1948 (48PM) method, the Penman-Van Bavel (PVB) method, the Baier-Robertson (B-R) method, the improved Baier-Robertson (M-B-R) method, the Schendel (Sch) method, the Turc method, the Jensen-Haise (J-H) method, and the Brutsaert-Stricker (B-S) method were used to evaluate the daily climatological data collected by 26 weather stations in Jiangxi, China, and 17 weather stations in adjacent provinces. The results were compared with each other and parameter rate determination was conducted. The results indicated that the Turc method exhibited optimized applicability before parameter rate determination and the average root mean square error (RMSE) and the average normalized root mean square error (NRMSE) by this method were 0.39 mm/d and 0.157 mm, respectively. However, parameter rate determination led to negligible improvement in accuracy for this method. The Turc method could be directly applied in Jiangxi (except Nanchang). For special distribution of error after parameter rate determination, all methods exhibited significant errors in Northern Jiangxi. Herein, the 48PM method and the B-S method showed good applicability after parameter rate determination and RMSE and NRMSE of data by these methods ranged in 0.06 ~ 0.34 mm/d and 0.08 ~ 0.27, 8 ~ 27%, respectively, and their d-indices were close to 1. The annual over-estimations in weather stations in Jiangxi were below 30 mm. In the absence of data about relative humidity and wind speed, the P–T method was an appropriate simplified method for Jiangxi. In this case, α was slightly lower than the default value (1.05 ~ 1.18), RMSE was within 0.21 ~ 0.66 mm/d, and NRMSE was within 0.08 ~ 0.308 ~ 30%. Accuracy of RMSE, d-index, and NRMSE of data by the P–T method, the I-A method, and the PVB method was consistent with all stations, while that by the Mak method was slightly lower, which could be attributed to severe over-estimation in July and August. RMSE of the H–S method, the B-R method, the M-B-R method, the J-H method, and the Sch method were above 0.75 mm/d and these methods were not suitable for accurate evaluation of ET0 in Jiangxi, China. The annual ET0 was calculated by various methods (except the 48PM method and the B-S method) exhibited significant variation around 2003. This may be attributed to significant changes in certain meteorological factors over recent years.

  相似文献   

20.
The objective of this study was to test an artificial neural network (ANN) for estimating the evaporation from pan (E Pan) as a function of air temperature data in the Safiabad Agricultural Research Center (SARC) located in Khuzestan plain in the southwest of Iran. The ANNs (multilayer perceptron type) were trained to estimate E Pan as a function of the maximum and minimum air temperature and extraterrestrial radiation. The data used in the network training were obtained from a historical series (1996–2001) of daily climatic data collected in weather station of SARC. The empirical Hargreaves equation (HG) is also considered for the comparison. The HG equation calibrated for converting grass evapotranspiration to open water evaporation by applying the same data used for neural network training. Two historical series (2002–2003) were utilized to test the network and for comparison between the ANN and calibrated Hargreaves method. The results show that both empirical and neural network methods provided closer agreement with the measured values (R 2?>?0.88 and RMSE?<?1.2 mm day?1), but the ANN method gave better estimates than the calibrated Hargreaves method.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号