Artificial Neural Networks Application to Predict Wheat Yield Using Climatic Data

The goal of this study was to apply artificial neural networks to predict rain-fed wheat yield using meteorological data a few days to few months before harvesting. The climatic observation data used; were mean of daily minimum and maximum temperature, extreme of daily minimum and maximum temperature, sum of daily rainfall, number of rainy days, sum of daily sun hours, mean of daily wind speed, extreme of daily wind speed, mean of daily relative humidity, and sum of daily water requirements that were collected during 1990-1999 in Sararood Station for wheat phenological stages consisting; sowing, germination, emergence, 3rd leaves, tillering, stem formation, heading, flowering, milk maturity, wax maturity, full maturity, separately for each growing season. Then, they arranged in a matrix whose rows form each of the statistical years and the columns are meteorological factors at each phenological stage. Finally, the obtained model had the following capabilities： Prediction of wheat yield with maximum errors of 45-60 kg/ha at least two months before full maturity stage, determination of the sensitivity of each phenological stage with respect to meteorological factors, and determination of the priority order and importance of each meteorological factor effective in plant growth and crop yield.

Modelling the impact of climate change on rangeland forage production using a generalized regression neural network:a case study in Isfahan Province,Central Iran

Monitoring of rangeland forage production at specified spatial and temporal scales is necessary for grazing management and also for implementation of rehabilitation projects in rangelands. This study focused on the capability of a generalized regression neural network（GRNN） model combined with GIS techniques to explore the impact of climate change on rangeland forage production. Specifically, a dataset of 115 monitored records of forage production were collected from 16 rangeland sites during the period 1998–2007 in Isfahan Province, Central Iran. Neural network models were designed using the monitored forage production values and available environmental data（including climate and topography data）, and the performance of each network model was assessed using the mean estimation error（MEE）, model efficiency factor（MEF）, and correlation coefficient（r）. The best neural network model was then selected and further applied to predict the forage production of rangelands in the future（in 2030 and 2080） under A1 B climate change scenario using Hadley Centre coupled model. The present and future forage production maps were also produced. Rangeland forage production exhibited strong correlations with environmental factors, such as slope, elevation, aspect and annual temperature. The present forage production in the study area varied from 25.6 to 574.1 kg/hm^2. Under climate change scenario, the annual temperature was predicted to increase and the annual precipitation was predicted to decrease. The prediction maps of forage production in the future indicated that the area with low level of forage production（0–100 kg/hm^2） will increase while the areas with moderate, moderately high and high levels of forage production（≥100 kg/hm^2） will decrease both in 2030 and in 2080, which may be attributable to the increasing annual temperature and decreasing annual precipitation. It was predicted that forage production of rangelands will decrease in the next couple of decades, especially in the western and southern parts of Isfahan Province. These changes are more pronounced in elevations between 2200 and 2900 m. Therefore, rangeland managers have to cope with these changes by holistic management approaches through mitigation and human adaptations.

Machine learning ensemble model prediction of northward shift in potato cyst nematodes(Globodera rostochiensis and G.pallida)distribution under climate change conditions

Potato cyst nematodes(PCNs)are a significant threat to potato production,having caused substantial damage in many countries.Predicting the future distribution of PCN species is crucial to implementing effective biosecurity strategies,especially given the impact of climate change on pest species invasion and distribution.Machine learning(ML),specifically ensemble models,has emerged as a powerful tool in predicting species distributions due to its ability to learn and make predictions based on complex data sets.Thus,this research utilised advanced machine learning techniques to predict the distribution of PCN species under climate change conditions,providing the initial element for invasion risk assessment.We first used Global Climate Models to generate homogeneous climate predictors to mitigate the variation among predictors.Then,five machine learning models were employed to build two groups of ensembles,single-algorithm ensembles(ESA)and multi-algorithm ensembles(EMA),and compared their performances.In this research,the EMA did not always perform better than the ESA,and the ESA of Artificial Neural Network gave the highest performance while being cost-effective.Prediction results indicated that the distribution range of PCNs would shift northward with a decrease in tropical zones and an increase in northern latitudes.However,the total area of suitable regions will not change significantly,occupying 16-20%of the total land surface(18%under current conditions).This research alerts policymakers and practitioners to the risk of PCNs’incursion into new regions.Additionally,this ML process offers the capability to track changes in the distribution of various species and provides scientifically grounded evidence for formulating long-term biosecurity plans for their control.

Estimating Monthly Surface Air Temperature Using MODIS LST Data and an Artificial Neural Network in the Loess Plateau, China

Air temperature(Ta)datasets with high spatial and temporal resolutions are needed in a wide range of applications,such as hydrology,ecology,agriculture,and climate change studies.Nonetheless,the density of weather station networks is insufficient,especially in sparsely populated regions,greatly limiting the accuracy of estimates of spatially distributed Ta.Due to their continuous spatial coverage,remotely sensed land surface temperature(LST)data provide the possibility of exploring spatial estimates of Ta.However,because of the complex interaction of land and climate,retrieval of Ta from the LST is still far from straightforward.The estimation accuracy varies greatly depending on the model,particularly for maximum Ta.This study estimated monthly average daily minimum temperature(Tmin),average daily maximum temperature(Tmax)and average daily mean temperature(Tmean)over the Loess Plateau in China based on Moderate Resolution Imaging Spectroradiometer(MODIS)LST data(MYD11A2)and some auxiliary data using an artificial neural network(ANN)model.The data from 2003 to 2010 were used to train the ANN models,while 2011 to 2012 weather station temperatures were used to test the trained model.The results showed that the nighttime LST and mean LST provide good estimates of Tmin and Tmean,with root mean square errors(RMSEs)of 1.04℃ and 1.01℃,respectively.Moreover,the best RMSE of Tmax estimation was 1.27℃.Compared with the other two published Ta gridded datasets,the produced 1 km×1 km dataset accurately captured both the temporal and spatial patterns of Ta.The RMSE of Tmin estimation was more sensitive to elevation,while that of Tmax was more sensitive to month.Except for land cover type as the input variable,which reduced the RMSE by approximately 0.01℃,the other vegetation-related variables did not improve the performance of the model.The results of this study indicated that ANN,a type of machine learning method,is effective for long-term and large-scale Ta estimation.

Climate change impacts on the streamflow of Zarrineh River,Iran

Zarrineh River is located in the northwest of Iran,providing more than 40%of the total inflow into the Lake Urmia that is one of the largest saltwater lakes on the earth.Lake Urmia is a highly endangered ecosystem on the brink of desiccation.This paper studied the impacts of climate change on the streamflow of Zarrineh River.The streamflow was simulated and projected for the period 1992-2050 through seven CMIP5(coupled model intercomparison project phase 5)data series(namely,BCC-CSM1-1,BNU-ESM,CSIRO-Mk3-6-0,GFDL-ESM2G,IPSL-CM5A-LR,MIROC-ESM and MIROC-ESM-CHEM)under RCP2.6(RCP,representative concentration pathways)and RCP8.5.The model data series were statistically downscaled and bias corrected using an artificial neural network(ANN)technique and a Gamma based quantile mapping bias correction method.The best model(CSIRO-Mk3-6-0)was chosen by the TOPSIS(technique for order of preference by similarity to ideal solution)method from seven CMIP5 models based on statistical indices.For simulation of streamflow,a rainfall-runoff model,the hydrologiska byrans vattenavdelning(HBV-Light)model,was utilized.Results on hydro-climatological changes in Zarrineh River basin showed that the mean daily precipitation is expected to decrease from 0.94 and 0.96 mm in 2015 to 0.65 and 0.68 mm in 2050 under RCP2.6 and RCP8.5,respectively.In the case of temperature,the numbers change from 12.33℃ and 12.37℃ in 2015 to 14.28℃ and 14.32℃ in 2050.Corresponding to these climate scenarios,this study projected a decrease of the annual streamflow of Zarrineh River by half from 2015 to 2050 as the results of climatic changes will lead to a decrease in the annual streamflow of Zarrineh River from 59.49 m^(3)/s in 2015 to 22.61 and 23.19 m^(3)/s in 2050.The finding is of important meaning for water resources planning purposes,management programs and strategies of the Lake's endangered ecosystem.

Climate Change Impacts on the Extreme Rainfall for Selected Sites in North Western England

Impact and adaptation assessments of climate change often require more detailed information of future extreme rainfall events at higher resolution in space and/or time, which is usually, projected using the Global Climate Model (GCM) for different emissions of greenhouse concentration. In this paper, future rainfall in the North West region of England has been generated from the outputs of the HadCM3 Global Climate Model through downscaling , employing a hybrid Generalised Linear Model (GLM) together with an Artificial Neural Network (ANN). Using two emission scenarios (A1FI and B1), the hybrid downscaling model was proven to have the capability to successfully simulate future rainfall. A combined peaks-over-threshold (POT)-Generalised Pareto Distribution approach was then used to model the extreme rainfall and then assess changes to seasonal trends over the region at a daily scale until the end of the 21st century. In general, extreme rainfall is predicted to be more frequent in winter seasons for both high (A1FI) and low (B1) scenarios, however for summer seasons, the region is predicted to experience some increase in extreme rainfall under the high scenario and a drop under the low scenario. The variation in intensity of extreme rainfall was found to be based on location,season, future period, return period as well as the emission scenario used.

Land use change modeling through an integrated Multi-Layer Perceptron Neural Network and Markov Chain analysis(case study: Arasbaran region, Iran)

Temporal land use/land cover (LULC) change information provides a variety of applications for informed management of land resources. The aim of this study was to detect and predict LULC changes in the Arasbaran region using an integrated Multi-Layer Perceptron Neural Network and Markov Chain analysis. At the first step, multi-temporal Landsat images (1990, 2002 and 2014) were processed using ancillary data and were classified into seven LULC categories of high density forest, low-density forest, agriculture, grassland, barren land, water and urban area. Next, LULC changes were detected for three time profiles, 1990–2002, 2002–2014 and 1990–2014. A 2014 LULC map of the study area was further simulated (for model performance evaluation) applying 1990 and 2002 map layers. In addition, a collection of spatial variables was also used for modeling LULC change processes as driving forces. The actual and simulated 2014 LULC change maps were cross-tabulated and compared to ensure model simulation success and the results indicated an overall accuracy and kappa coefficient of 97.79% and 0.992, respectively. Having the model properly validated, LULC change was predicted up to the year 2025. The results demonstrated that 992 and 1592 ha of high and lowdensity forests were degraded during 1990–2014,respectively, while 422 ha were added to the extent of residential areas with a growth rate of 17.58 ha per year. The developed model predicted a considerable degradation trend for the forest categories through 2025, accounting for 489 and 531 ha of loss for high and low-density forests, respectively. By way of contrast, residential area and farmland categories will increase up to 211 and 427 ha, respectively. The integrated prediction model and customary area data can be used for practical management efforts by simulating vegetation dynamics and future LULC change trajectories.

Predicting the impacts of climate change on nonpoint source pollutant loads from agricultural small watershed using artificial neural network

This study described the development and validation of an artificial neural network （ANN） for the purpose of analyzing the effects of climate change on nonpoint source （NPS） pollutant loads from agricultural small watershed. The runoff discharge was estimated using ANN algorithm. The performance of ANN model was examined using observed data from study watershed. The simulation results agreed well with observed values during calibration and validation periods. NPS pollutant loads were calculated from load-discharge relationship driven by long-term monitoring data. LARS-WG （Long Ashton Research Station-Weather Generator） model was used to generate rainfall data. The calibrated ANN model and load-discharge relationship with the generated data from LARS-WG were applied to analyze the effects of climate change on NPS pollutant loads from the agricultural small watershed. The results showed that the ANN model provided valuable approach in estimating future runoff discharge, and the NPS pollutant loads.

Application of artificial neural networks in global climate change and ecological research:An overview

Fields that employ artificial neural networks(ANNs)have developed and expanded continuously in recent years with the ongoing development of computer technology and artificial intelligence.ANN has been adopted widely and put into practice by research-ers in light of increasing concerns over ecological issues such as global warming,frequent El Nio-Southern Oscillation(ENSO)events,and atmospheric circulation anomalies.Limitations exist and there is a potential risk for misuse in that ANN model pa-rameters require typically higher overall sensitivity,and the chosen network structure is generally more dependent upon individ-ual experience.ANNs,however,are relatively accurate when used for short-term predictions;despite global climate change re-search favoring the effects of interactions as the basis of study and the preference for long-term experimental research.ANNs remain a better choice than many traditional methods when dealing with nonlinear problems,and possesses great potential for the study of global climate change and ecological issues.ANNs can resolve problems that other methods cannot.This is especially true for situations in which measurements are difficult to conduct or when only incomplete data are available.It is anticipated that ANNs will be widely adopted and then further developed for global climate change and ecological research.

Performance and uncertainty analysis of a short-term climate reconstruction based on multi-source data in the Tianshan Mountains region,China

Short-term climate reconstruction,i.e.,the reproduction of short-term(several decades)historical climatic time series based on the relationship between observed data and available longer-term reference data in a certain area,can extend the length of climatic time series and offset the shortage of observations.This can be used to assess regional climate change over a much longer time scale.Based on monthly grid climate data from a Coupled Model Inter-comparison Project phase 5(CMIP5)dataset for the period of 1850–2000,the Climatic Research Unit(CRU)dataset for the period of 1901–2000 and the observed data from 53 meteorological stations located in the Tianshan Mountains region(TMR)of China during the period of 1961–2011,we calibrated and validated monthly average temperature(MAT)and monthly accumulated precipitation(MAP)in the TMR using the delta,physical scaling(SP)and artificial neural network(ANN)methods.Performance and uncertainty during the calibration(1971–1999)and verification(1961–1970)periods were assessed and compared using traditional performance indices and a revised set pair analysis(RSPA)method.The calibration and verification processes were subjected to various sources of uncertainty due to the influence of different reconstructed variables,different data sources,and/or different methods used.According to traditional performance indices,both the CRU and CMIP5 datasets resulted in satisfactory calibrated and verified MAT time series at 53 meteorological stations and MAP time series at 20 meteorological stations using the delta and SP methods for the period of 1961–1999.However,the results differed from those obtained by the RSPA method.This showed that the CRU dataset produced a low degree of uncertainty(positive connection degree)during the calibration and verification of MAT using the delta and SP methods compared to the CMIP5 dataset.Overall,the calibrated and verified MAP had a high degree of uncertainty(negative connection degree)regardless of the dataset or reconstruction method used.Therefore,the reconstructed time series of MAT for the period of 1850(or 1901)–1960 based on the CRU and CMIP5 datasets using the delta and SP methods could be used for further study.The results of this study will be useful for short-term(several decades)regional climate reconstruction and longer-term(100 a or more)assessments of regional climate change.

The Application of BP Neural Networks to Analysis the National Vulnerability

Climate change is the main factor affecting the country’s vulnerability,meanwhile,it is also a complicated and nonlinear dynamic system.In order to solve this complex problem,this paper first uses the analytic hierarchy process(AHP)and natural breakpoint method(NBM)to implement an AHP-NBM comprehensive evaluation model to assess the national vulnerability.By using ArcGIS,national vulnerability scores are classified and the country’s vulnerability is divided into three levels:fragile,vulnerable,and stable.Then,a BP neural network prediction model which is based on multivariate linear regression is used to predict the critical point of vulnerability.The function of the critical point of vulnerability and time is established through multiple linear regression analysis to obtain the regression equation.And the proportion of each factor in the equation is established by using the partial least-squares regression to select the main factors affecting the country’s vulnerability,and using the neural network algorithm to perform the fitting.Lastly,the BP neural network prediction model is optimized by genetic algorithm to get the chaotic time series BP neural network prediction model.In order to verify the practicability of the model,Cambodia is selected to be an example to analyze the critical point of the national vulnerability index.

A Hybrid Method for Compression of Solar Radiation Data Using Neural Networks

The prediction of solar radiation is important for several applications in renewable energy research. There are a number of geographical variables which affect solar radiation prediction, the identification of these variables for accurate solar radiation prediction is very important. This paper presents a hybrid method for the compression of solar radiation using predictive analysis. The prediction of minute wise solar radiation is performed by using different models of Artificial Neural Networks (ANN), namely Multi-layer perceptron neural network (MLPNN), Cascade feed forward back propagation (CFNN) and Elman back propagation (ELMNN). Root mean square error (RMSE) is used to evaluate the prediction accuracy of the three ANN models used. The information and knowledge gained from the present study could improve the accuracy of analysis concerning climate studies and help in congestion control.

A Hybrid Neural Network-based Approach for Forecasting Water Demand

Water is a vital resource.It supports a multitude of industries,civilizations,and agriculture.However,climatic conditions impact water availability,particularly in desert areas where the temperature is high,and rain is scarce.Therefore,it is crucial to forecast water demand to provide it to sectors either on regular or emergency days.The study aims to develop an accurate model to forecast daily water demand under the impact of climatic conditions.This forecasting is known as a multivariate time series because it uses both the historical data of water demand and climatic conditions to forecast the future.Focusing on the collected data of Jeddah city,Saudi Arabia in the period between 2004 and 2018,we develop a hybrid approach that uses Artificial Neural Networks(ANN)for forecasting and Particle Swarm Optimization algorithm(PSO)for tuning ANNs’hyperparameters.Based on the Root Mean Square Error(RMSE)metric,results show that the(PSO-ANN)is an accurate model for multivariate time series forecasting.Also,the first day is the most difficult day for prediction(highest error rate),while the second day is the easiest to predict(lowest error rate).Finally,correlation analysis shows that the dew point is the most climatic factor affecting water demand.

Regional Climate Index for Floods and Droughts Using Canadian Climate Model (CGCM3.1)

The impacts of climate change on the discharge regimes in New Brunswick (Canada) were analyzed, using artificial neural network models. Future climate data were extracted from the Canadian Coupled General Climate Model (CGCM3.1) under the greenhouse gas emission scenarios B1 and A2 defined by the Intergovernmental Panel on Climate Change (IPCC). The climate change fields (temperatures and precipitation) were downscaled using the delta change approach. Using the artificial neural network, future river discharge was predicted for selected hydrometric stations. Then, a frequency analysis was carried out using the Generalized Extreme Value (GEV) distribution function, where the parameters of the distribution were estimated using L-moments method. Depending on the scenario and the time slice used, the increase in low return floods was about 30% and about 15% for higher return floods. Low flows showed increases of about 10% for low return droughts and about 20% for higher return droughts. An important part of the design process using frequency analysis is the estimation of future change in floods or droughts under climate scenarios at a given site and for specific return periods. This was carried out through the development of Regional Climate Index (RCI), linking future floods and droughts to their frequencies under climate scenarios B1 and A2.

Study on Ann-Based Multi-Step Prediction Model of Short-Term Climatic Variation

In the context of 1905–1995 series from Nanjing and Hangzhou, study is undertaken of estab-lishing a predictive model of annual mean temperature in 1996–2005 to come over the Changjiang (Yangtze River) delta region through mean generating function and artificial neural network in combination. Results show that the established model yields mean error of 0.45°C for their abso-lute values of annual mean temperature from 10 yearly independent samples (1986–1995) and the difference between the mean predictions and related measurements is 0.156°C. The developed model is found superior to a mean generating function regression model both in historical data fit-ting and independent sample prediction. Key words Climate trend prediction. Mean generating function (MGF) - Artificial neural network (ANN) - Annual mean temperature (AMT)

MEPM模型:基于深度学习的多变量厄尔尼诺-南方涛动预测模型

厄尔尼诺-南方涛动(ENSO)是发生在热带太平洋年际时间尺度的海-气相互作用的异常现象,并由Nino3.4指数表征其发生情况;除此之外,ENSO与众多极端气候事件密切相关。因此,有效的ENSO预测对于预防极端气候事件和深入研究全球气候变化具有重要意义。然而,目前基于深度学习的ENSO预测大多数是预测一个指数或者单一变量,对于模拟多气候要素下的ENSO预测研究较少。通过提出一种利用多气候变量的ENSO预测模型——MEPM模型,其中包括多变量信息提取模块(MIEM)和时空融合模块(STFM),捕获不同气候变量在时空上的相互依赖性,进而提高ENSO预测的准确性。选取了纬向风应力异常(τ_(x))、经向风应力异常(τ_(y))、海表温度异常(SSTA)和海表下150 m温度异常(SSTA150)4个变量的距平值进行ENSO预测。结果表明:MEPM模型在提前11个月的Nino3.4指数相关技巧上分别比北美多模型集合中的动力预报系统CanCM4、CCSM3和GFDL-aer04高10%、20%和14%。此外,MEPM模型在中期Nino3.4指数相关技巧上显著优于其他深度学习模型,并可提供长达17个月的有效预测。

基于神经网络的风暴潮增水对海岸带城市排水的影响分析--以青岛市为例

本文以青岛市为研究区域,以0509台风风暴潮增水水位数据为基础,基于BP(Back propagation)神经网络,考虑地形地势特性中易涝因子,并结合水文分析提取入海排水口的空间分布,对青岛市沿海岸排水受风暴潮影响的区域进行预测,并进一步结合青岛市沿海岸,系统探讨气候变化背景下风暴潮增水对青岛市沿海岸排水的影响。结果表明:除风暴潮增水直接侵袭至陆地内侧区域,青岛大江口湾岸段、浮山湾岸段、汇泉湾岸段、青岛湾岸段、胶州湾东南侧岸段海泊河沿岸等区域在各类情景下排水受风暴潮增水影响较大。

深度学习在印度洋偶极子预测中的应用研究综述

印度洋偶极子(Indian Ocean Dipole,IOD)是影响区域及全球气候变化的关键气候现象。准确预测IOD对于理解全球气候至关重要,但传统方法在捕捉其复杂性和非线性方面的局限限制了预测能力。该文首先概述了IOD的相关理论,并评估了传统预测方法的优缺点。然后,综合分析了深度学习在IOD预测领域的应用和发展,特别强调了深度学习模型在自动特征提取、非线性关系建模和大数据处理方面相较于传统方法的优势。与此同时,该文还讨论了深度学习模型在IOD预测中所面临的挑战,包括数据稀缺、过拟合以及模型可解释性等问题,并提出了未来研究的方向,旨在推动深度学习技术在气候预测领域的创新与进步。

基于BP神经网络的长鳍金枪鱼渔获量与气候因子关系研究

为探讨气候变化对长鳍金枪鱼渔获量的影响,利用中西太平洋渔业委员会统计的1960-2021年太平洋长鳍金枪鱼年度渔获量和对应的厄尔尼诺指标(Niño1+2、Niño3、Niño4以及Niño3.4)、南方涛动指数(SOI)、北大西洋涛动(NAO)、太平洋年代际涛动(PDO)、北太平洋指数(NPI)以及全球海气温度异常指标(dT)等月度数据,采用BP神经网络和变量敏感性分析法探讨了低频气候因子与长鳍金枪鱼渔获量的关系;构建了结构为6-8-1的最优BP神经网络模型,对长鳍金枪鱼渔获量进行了预测。结果表明,Niño1+2、SOI、NAO、PDO、NPI、dT为影响长鳍金枪鱼渔获量相对独立的气候因子,其对应的最佳滞后阶数依次为8年、2年、9年、0年、9年、3年。Niño1+2、SOI、NAO为影响长鳍金枪鱼渔获量的关键气候因子。长鳍金枪鱼渔获量预测值和实际值差值与实际值的比值自1971年后基本维持在15%以内,预测值与实际值变化趋势基本一致,模型拟合效果良好。