Neural network classification of tan spot and stagonospora blotch infection periods in a wheat field environment

ABSTRACT Tan spot and Stagonospora blotch of hard red spring wheat served as a model system for evaluating disease forecasts by artificial neural networks. Pathogen infection periods on susceptible wheat plants were measured in the field from 1993 to 1998, and incidence data were merged with 24-h summaries of accumulated growing degree days, temperature, relative humidity, precipitation, and leaf wetness duration. The resulting data set of 202 discrete periods was randomly assigned to 10 modeldevelopment or -validation (n = 50) data sets. Backpropagation neural networks, general regression neural networks, logistic regression, and parametric and nonparametric methods of discriminant analysis were chosen for comparison. Mean validation classification of tan spot incidence was between 71% for logistic regression and 76% for backpropagation models. No significant difference was found between methods of modeling tan spot infection periods. Mean validation prediction accuracy of Stagonospora blotch incidence was 86 and 81% for backpropagation and logistic regression, respectively. Prediction accuracies of other modeling methods were 相似文献   

Neural networks that distinguish infection periods of wheat tan spot in an outdoor environment

ABSTRACT Tan spot of wheat, caused by Pyrenophora tritici-repentis, provided a model system for testing disease forecasts based on an artificial neural network. Infection periods for P. tritici-repentis on susceptible wheat cultivars were identified from a bioassay system that correlated tan spot incidence with crop growth stage and 24-h summaries of environmental data, including temperature, relative humidity, wind speed, wind direction, solar radiation, precipitation, and flat-plate resistance-type wetness sensors. The resulting data set consisted of 97 discrete periods, of which 32 were reserved for validation analysis. Neural networks with zero to nine processing elements were evaluated 20 times each to identify the model that most accurately predicted an infection event. The 200 models averaged 74 to 77% accuracy, depending on the number of processing elements and random initialization of coefficients. The most accurate model had five processing elements and correctly predicted 87% of the infection periods in the validation set. In comparison, stepwise logistic regression correctly predicted 69% of the validation cases, and multivariate discriminant analysis distinguished 50% of the validation cases. When wetness-sensor inputs were withheld from the models, both the neural network and logistic regression models declined 6% in prediction accuracy. Thus, neural networks were more accurate than statistical procedures, both with and without wetness-sensor inputs. These results demonstrate the applicability of neural networks to plant disease forecasting.     

Weather-based prediction of anthracnose severity using artificial neural network models

Data were collected and analysed from seven field sites in Australia, Brazil and Colombia on weather conditions and the severity of anthracnose disease of the tropical pasture legume Stylosanthes scabra caused by Colletotrichum gloeosporioides . Disease severity and weather data were analysed using artificial neural network (ANN) models developed using data from some or all field sites in Australia and/or South America to predict severity at other sites. Three series of models were developed using different weather summaries. Of these, ANN models with weather for the day of disease assessment and the previous 24 h period had the highest prediction success, and models trained on data from all sites within one continent correctly predicted disease severity in the other continent on more than 75% of days; the overall prediction error was 21·9% for the Australian and 22·1% for the South American model. Of the six cross-continent ANN models trained on pooled data for five sites from two continents to predict severity for the remaining sixth site, the model developed without data from Planaltina in Brazil was the most accurate, with >85% prediction success, and the model without Carimagua in Colombia was the least accurate, with only 54% success. In common with multiple regression models, moisture-related variables such as rain, leaf surface wetness and variables that influence moisture availability such as radiation and wind on the day of disease severity assessment or the day before assessment were the most important weather variables in all ANN models. A set of weights from the ANN models was used to calculate the overall risk of anthracnose for the various sites. Sites with high and low anthracnose risk are present in both continents, and weather conditions at centres of diversity in Brazil and Colombia do not appear to be more conducive than conditions in Australia to serious anthracnose development.     

陕西小麦条锈病发生面积预测模型

为提高陕西省小麦条锈病发生面积的预测准确度,以2010年-2018年陕西省小麦条锈菌冬繁区和越冬区的发生县区数、发生面积、温度和降雨量为数据集,通过Pearson相关性分析筛选病害流行的主要影响因子,利用全子集回归筛选病害流行的因子集。以筛选得到的影响病害流行的5个因子,即累计发生县区数、冬繁区条锈病发生面积、1月平均温度、1月平均降雨量和3月平均降雨量为自变量,采用全子集回归和BP神经网络算法开展小麦条锈病发生面积的预测研究。结果表明,全子集回归和BP神经网络算法对2019年-2020年的小麦条锈病发生面积预测准确度均达90%以上,预测2021年陕西省小麦条锈病发生面积分别为46.11万hm~2和52.85万hm~2。     

Risk assessment models for wheat fusarium head blight epidemics based on within-season weather data

ABSTRACT Logistic regression models for wheat Fusarium head blight were developed using information collected at 50 location-years, including four states, representing three different U.S. wheat-production regions. Non-parametric correlation analysis and stepwise logistic regression analysis identified combinations of temperature, relative humidity, and rainfall or durations of specified weather conditions, for 7 days prior to anthesis, and 10 days beginning at crop anthesis, as potential predictor variables. Prediction accuracy of developed logistic regression models ranged from 62 to 85%. Models suitable for application as a disease warning system were identified based on model prediction accuracy, sensitivity, specificity, and availability of weather variables at crop anthesis. Four of the identified models correctly classified 84% of the 50 location-years. A fifth model that used only pre-anthesis weather conditions correctly classified 70% of the location-years. The most useful predictor variables were the duration (h) of precipitation 7 days prior to anthesis, duration (h) that temperature was between 15 and 30 degrees C 7 days prior to anthesis, and the duration (h) that temperature was between 15 and 30 degrees C and relative humidity was greater than or equal to 90%. When model performance was evaluated with an independent validation set (n = 9), prediction accuracy was only 6% lower than the accuracy for the original data sets. These results indicate that narrow time periods around crop anthesis can be used to predict Fusarium head blight epidemics.     

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.     

Improving soil heat and moisture forecasting for arid and semi-arid regions: A comparative study of four mathematical algorithms

Mathematical modeling is extensively used for ecohydrological processes because it facilitates data acquisition. However, modeling of soil moisture and heat remains challenging in dry ecosystems. In this study, we examined the performance of four models in simulating hydrological processes in a semi-arid mountain grassland (SMG), and in shrubland forming a transitional zone between the desert and an oasis (desert–oasis ecotone; DOE) in northwestern China. We used precipitation, air temperature, humidity, atmospheric pressure, and other meteorological variables to estimate moisture and temperature at different soil depths. Four methods were used to test model performance, including partial least squares (PLS) regression, stepwise multiple linear regression (SMR), back-propagation artificial neural network (BPANN), and neural network time series. Our results showed that BPANN had the best prediction accuracy and supplied a robust modeling framework capable of capturing nonlinear environmental processes by improving the stability of the weight-learning process. Soil depth in SMG for which model performance was optimized was 20?cm for PLS and SMR. Additionally, artificial neural networks (ANNs) have a remarkable applicability compared to other algorithms for increased accuracy in time-series predictions; however, they could not depict soil moisture or temperature dynamics at 160?cm depth in SMG, and at 10?cm depth in DOE. Using conventional meteorological data as primary predictors, and avoiding the complexity of distributed hydrological models can be helpful in developing a regional capacity for soil moisture and heat forecasting.     

基于气象因子驱动的阴山地区马铃薯产量预测模型

为了及时掌握马铃薯产量,提高产中、产后气象服务能力,指导马铃薯生产,以内蒙古阴山旱作区马铃薯生产为例,利用16个旗县1980-2007年气象和产量资料及发育期等其它相关资料,采用相关和回归分析等方法,分区域分析了影响马铃薯产量的关键气象因子,并建立了气象产量预测模型.结果表明:(1)降水是影响产量的关键因子,温度次之;前山地区高温胁迫的影响大于后山,降水不足的影响则相反;干旱少雨、高温胁迫是制约该地区马铃薯产量提高的主要因素.(2)用逐步回归方法建立的幼苗期-结薯期、幼苗期-淀粉积累期、结薯期-淀粉积累期和生长季4个时间段的气象产量预测模型均达到极显著水平,拟合率75％以上,产量预测平均误差11.1％,误差变幅0.34％ ～ 27.9％,近85％的预测值准确率超出80％,对区域预测结果好于各旗县;(3)结薯期是对水热最敏感的时期;不同时间段模型中以生长季和幼苗-结薯期模型预测结果较好.所建模型可以在马铃薯产量预测业务中应用.     

西北地区小麦黄矮病流行分析及人工神经网络模型的构建

对西北地区半干旱气候区小麦黄矮病1992—2009年发生、流行情况进行长期监测、分析,选择制约小麦黄矮病发生、流行的23个因素,利用三层人工神经网络可以逼近任意连续函数,对非线性预测系统进行模拟处理的特点,分析所选预测分子,提出一套完整的建立BP人工神经网络模型的方法,并建立陕西省BP神经网络长期预测模型。对1992—2006年数据进行网络训练,利用2007—2009年数据进行测试。结果表明,以发病率为指标,输出结果误差在0.001~0.034之间;以发病级别作为预测结果,模型计算得出的数值与实际病级完全吻合,准确率为100%。说明利用神经网络建立小麦黄矮病预测模型是可行的。     

适用于我国的稻纵卷叶螟长期预测模型

为给我国稻纵卷叶螟Cnaphalocrocis medinalis防治提供前期预警,使用R语言软件对我国15个省市区稻纵卷叶螟发生等级与全球海温场资料进行遥相关分析,绘制相关系数的时空间分布图,筛选出显著相关海温区作为预测因子,根据各省市区虫情数据组建回归模型+判别模型、BP神经网络模型和支持向量机(SVM)模型,比较3种模型的历史回检率和预测完全准确率。结果显示,3种模型对稻纵卷叶螟发生等级均有一定的预测能力,其中判别模型+回归模型效果最好,预检完全准确率可达到75.0%,BP神经网络模型次之,预检完全准确率为68.2%,SVM模型预测效果最差,预检完全准确率为54.5%。进一步分析建模所使用的50个预测因子的空间位置,在南印度洋和北大西洋确定3个预测指标,预检准确率为94.4%。通过海温场数据建立的我国15个省市区稻纵卷叶螟发生等级预测模型,适用于长期预测预报。判别模型+回归模型更适合在样本量少、预测因子相关性强的地区建模,而根据预测因子空间分布选择的预测指标进行定性预测准确率更高。     

甜菜夜蛾发生程度的气象等级预报模型

甜菜夜蛾是严重影响蔬菜产量和品质的害虫,其发生发展与气象条件关系十分密切。为探索气象条件与甜菜夜蛾发生程度的关系,开展甜菜夜蛾发生程度气象等级预报服务,选取2009—2010年湖北省甜菜夜蛾虫情资料和对应台站的气象资料,对甜菜夜蛾发生程度等级与各项气象因子做相关分析,在此基础上,筛选出模型因子,采用多元线性回归分析方法,构建了湖北省甜菜夜蛾发生程度气象等级预报模型,并对模型验证。结果表明:历史回代检验旬检验结果达基本一致以上的为76%;独立样本预测检验旬值达基本一致以上的为63%,模型总体预报结果较好,可为湖北省开展甜菜夜蛾气象等级预报业务提供技术支撑。     

Rainfall and temperature distinguish between Karnal bunt positive and negative years in wheat fields in Texas

Karnal bunt of wheat, caused by the fungus Tilletia indica, is an internationally regulated disease. Since its first detection in central Texas in 1997, regions in which the disease was detected have been under strict federal quarantine regulations resulting in significant economic losses. A study was conducted to determine the effect of weather factors on incidence of the disease since its first detection in Texas. Weather variables (temperature and rainfall amount and frequency) were collected and used as predictors in discriminant analysis for classifying bunt-positive and -negative fields using incidence data for 1997 and 2000 to 2003 in San Saba County. Rainfall amount and frequency were obtained from radar (Doppler radar) measurements. The three weather variables correctly classified 100% of the cases into bunt-positive or -negative fields during the specific period overlapping the stage of wheat susceptibility (boot to soft dough) in the region. A linear discriminant-function model then was developed for use in classification of new weather variables into the bunt occurrence groups (+ or -). The model was evaluated using weather data for 2004 to 2006 for San Saba area (central Texas), and data for 2001 and 2002 for Olney area (north-central Texas). The model correctly predicted bunt occurrence in all cases except for the year 2004. The model was also evaluated for site-specific prediction of the disease using radar rainfall data and in most cases provided similar results as the regional level evaluation. The humid thermal index (HTI) model (widely used for assessing risk of Karnal bunt) agreed with our model in all cases in the regional level evaluation, including the year 2004 for the San Saba area, except for the Olney area where it incorrectly predicted weather conditions in 2001 as unfavorable. The current model has a potential to be used in a spray advisory program in regulated wheat fields.     

一种基于误差分级的土壤水分数据同化方法

将多源观测数据同化到生态模型中,可以更好地估计土壤水分,然而如何准确估计土壤水分遥感观测值的误差空间分布一直是数据同化中的难点。文中研究通过SPSI(Shortwave Infrared Perpendicular WaterStress Index)反演的土壤湿度作为观测值,分析SPSI反演土壤水分的原理,提出了基于地表植被覆盖程度,分级反演土壤水分的方法,给予观测值不同的误差方差估计。文中选择中国的宁夏作为研究区,将分级反演的观测值与生态过程模型模拟的土壤水分进行数据同化。结果表明:这种方法能够有效地避免SPSI指数本身对植被覆盖度低或植被生物量小的地区的土壤水分估计误差较大而导致的同化结果的偏差,提高区域土壤水分同化结果的精度。     

Modeling spatio-temporal distribution of soil moisture by deep learning-based cellular automata model

Soil moisture content (SMC) is a key hydrological parameter in agriculture,meteorology and climate change,and understanding of spatio-temporal distributions of SMC in farmlands is important to address the precise irrigation scheduling.However,the hybrid interaction of static and dynamic environmental parameters makes it particularly difficult to accurately and reliably model the distribution of SMC.At present,deep learning wins numerous contests in machine learning and hence deep belief network (DBN) ,a breakthrough in deep learning is trained to extract the transition functions for the simulation of the cell state changes.In this study,we used a novel macroscopic cellular automata (MCA) model by combining DBN to predict the SMC over an irrigated corn field (an area of 22 km~2) in the Zhangye oasis,Northwest China.Static and dynamic environmental variables were prepared with regard to the complex hydrological processes.The widely used neural network,multi-layer perceptron (MLP) ,was utilized for comparison to DBN.The hybrid models (MLP-MCA and DBN-MCA) were calibrated and validated on SMC data within four months,i.e.June to September 2012,which were automatically observed by a wireless sensor network (WSN) .Compared with MLP-MCA,the DBN-MCA model led to a decrease in root mean squared error (RMSE) by 18%.Thus,the differences of prediction errors increased due to the propagating errors of variables,difficulties of knowing soil properties and recording irrigation amount in practice.The sequential Gaussian simulation (s Gs) was performed to assess the uncertainty of soil moisture estimations.Calculated with a threshold of SMC for each grid cell,the local uncertainty of simulated results in the post processing suggested that the probability of SMC less than 25% will be difference in different areas at different time periods.The current results showed that the DBN-MCA model performs better than the MLP-MCA model,and the DBN-MCA model provides a powerful tool for predicting SMC in highly non-linear forms.Moreover,because modeling soil moisture by using environmental variables is gaining increasing popularity,DBN techniques could contribute a lot to enhancing the calibration of MCA-based SMC estimations and hence provide an alternative approach for SMC monitoring in irrigation systems on the basis of canals.     

基于温湿系数的棉蚜发生等级预报模型

为实现棉蚜发生等级的预报,以新疆生产建设兵团第七师一二五团为研究区,在收集和获取该区2004—2013年气象资料和棉蚜发生数据的基础上,运用统计方法、相关性分析和多元回归分析法对影响棉蚜发生的主要气象因子进行研究,构建棉蚜发生等级预报模型。结果显示,研究区棉蚜发生发展呈现3个阶段:5—6月为发生期、7月为高峰期、8月为衰退期;温度、湿度、蒸发量、日照与棉蚜发生等级的相关系数分别是0.52、0.34、-0.06和-0.05,表明影响棉蚜发生等级的主要气象因子是温度和湿度,但二者与棉蚜阶段发生等级之间的回归拟合优度为0.55,线性相关关系不明显。探索性地融合温度和湿度构建温湿系数,以温湿系数的自然对数与棉蚜发生等级进行回归分析,发现发生期相对温湿系数的自然对数与棉蚜发生等级的回归拟合优度为0.65,高峰期和衰退期直接温湿系数的自然对数与棉蚜发生等级的回归拟合优度分别为0.89和0.91,均呈线性关系。用2014年研究区棉蚜数据验证建立的线性回归模型,整体准确率达87.5%,可满足棉蚜发生等级预报需求。     

VMD-LSTM模型对不同预见期月径流的预测研究

为减小径流时间序列的非线性及非平稳性带来的预测误差,提高多种预见期下的月径流预测精度,将变模态分解（VMD）和长短期记忆神经网络（LSTM）模型相结合,建立了VMD-LSTM组合预测模型,并将大气环流因子作为模型输入的增加项,预测未来1~3个月的月径流。将模型应用于黄河流域上游唐乃亥、民和、享堂、红旗及折桥站的月径流预测以验证模型的适用性,并与VMD-BP（BP神经网络）、VMD-SVR（支持向量回归）及单一LSTM模型相比较。结果表明：VMD-LSTM组合模型的预测误差最小、精度最高,相比单一LSTM模型,其纳什效率系数（NSE）约从0.6~0.7提高到0.9以上;融合大气环流因子后VMD-LSTM模型预测精度进一步提高,NSE保持在0.91~0.96之间;随着预见期的增长,VMD-LSTM模型预测精度衰减较VMD-BP和VMD-SVR模型明显变缓,在3个月预见期时NSE仍能保持在0.84~0.95之间。VMD-LSTM模型是月径流预测的一种有效方法,结果可为研究区月径流预测提供参考。     

土壤参数的光谱实时分析

使用ASDFR2500便携光谱仪对国家精准农业示范区原状土土壤水分、有机质、NO3-、EC和pH等参数进行了野外测定测评。用原反射率倒数的对数(A值)分别与各土壤参数建立的直线相关模型均取得较好相关结果。分析认为土壤有机质的测定选用762nm波段,NO3-光谱吸收波段在431nm时相关性最好,电导率选用1414nm作为测定波段为最佳。这些模型可作为土壤参数估测和评价的参考。     

内蒙古农牧交错带春季土壤底墒估算模式研究

利用内蒙古农牧交错区13个站点20a的土壤水分观测资料和常规气象资料,分析了前期不同时段降水量(R)和参考作物蒸散量(Eo)与春季实测底墒的关系,分别建立了不同生态气候经济类型地区0～50cm和0～20cm土层的底墒估算模型,并利用2001～2002年土壤湿度和相应的气象资料对模型进行了检验,预测准确率平均为91.1%。     

蚕豆蚜数量动态预测研究

为害蚕虫的主要蚜种Ａｐｈｉｓ ｃｒａｃｃｉｖｏｒａ Ｋｏｃｈ、Ａｃｙｒｔｈｏｓｉｐｈｏｎ ｐｉｓｕｍ （Ｈａｒｒｉｓ）、Ｍｅｇｏｕｒａ ｊａｐａｎｉｃａ Ｍａｔｓｕｍｕｒａ，在蚕豆生长的季节，其发生发展具有明显的阶段性，即迁入定居、数量波动、扩散蔓延及消退４个阶段。数量动态预测模型；     

基于MTVDI与DDI二元回归模型对毛乌素沙地腹部土壤表层水分的研究

采用温度植被干旱指数法(MTVDI)与荒漠化指数法(DDI),利用2016年4月、9月的Landsat数据对毛乌素沙地腹部的土壤水分进行反演,并与实测的土壤水分进行对比检验,将所反演的土壤含水量图划分为4个等级,基于此分析了2个时期毛乌素沙地腹部的旱情土壤水分分布变化。结果显示：(1)4月份MTVDI指数与0~10 cm、10~20 cm、20~30 cm土层土壤含水量的R²值分别为0.656、0.646、0.637,整体高于9月份R²值0.457、0.436、0.431,MTVDI能够较好地反映毛乌素沙地腹部土壤表层水分,且精度较高;(2)荒漠化指数DDI与MTVDI结合建立二元线性回归模型监测区域土层0~10 cm深度含水量,平均相对误差为10.95 %;(3)4月份,研究区0~10 cm表层土壤含水量5%~10%区域占总面积的53.72%以上,达到了6 256 km²,含水量偏低,需要加强当地水资源管理。