Operating at the extreme: estimating the upper yield boundary of winter wheat production in commercial practice

Wheat farming provides 28.5% of global cereal production. After steady growth in average crop yield from 1950 to 1990, wheat yields have generally stagnated, which prompts the question of whether further improvements are possible. Statistical studies of agronomic parameters such as crop yield have so far exclusively focused on estimating parameters describing the whole of the data, rather than the highest yields specifically. These indicators include the mean or median yield of a crop, or finding the combinations of agronomic traits that are correlated with increasing average yields. In this paper, we take an alternative approach and consider high yields only. We carry out an extreme value analysis of winter wheat yield data collected in England and Wales between 2006 and 2015. This analysis suggests that, under current climate and growing conditions, there is indeed a finite upper bound for winter wheat yield, whose value we estimate to be 17.60 tonnes per hectare. We then refine the analysis for strata defined by either location or level of use of agricultural inputs. We find that there is no statistical evidence for variation of maximal yield depending on location, and neither is there statistical evidence that maximum yield levels are improved by high levels of crop protection and fertilizer use.

Download Full-text

An Improved CASA Model for Estimating Winter Wheat Yield from Remote Sensing Images

Remote Sensing ◽

10.3390/rs11091088 ◽

2019 ◽

Vol 11 (9) ◽

pp. 1088 ◽

Cited By ~ 4

Author(s):

Yulong Wang ◽

Xingang Xu ◽

Linsheng Huang ◽

Guijun Yang ◽

Lingling Fan ◽

...

Keyword(s):

Remote Sensing ◽

Time Series ◽

Winter Wheat ◽

Crop Yield ◽

Satellite Remote Sensing ◽

Wheat Yield ◽

Growing Season ◽

Remote Sensing Images ◽

Casa Model ◽

Winter Wheat Yield

The accurate and timely monitoring and evaluation of the regional grain crop yield is more significant for formulating import and export plans of agricultural products, regulating grain markets and adjusting the planting structure. In this study, an improved Carnegie–Ames–Stanford approach (CASA) model was coupled with time-series satellite remote sensing images to estimate winter wheat yield. Firstly, in 2009 the entire growing season of winter wheat in the two districts of Tongzhou and Shunyi of Beijing was divided into 54 stages at five-day intervals. Net Primary Production (NPP) of winter wheat was estimated by the improved CASA model with HJ-1A/B satellite images from 39 transits. For the 15 stages without HJ-1A/B transit, MOD17A2H data products were interpolated to obtain the spatial distribution of winter wheat NPP at 5-day intervals over the entire growing season of winter wheat. Then, an NPP-yield conversion model was utilized to estimate winter wheat yield in the study area. Finally, the accuracy of the method to estimate winter wheat yield with remote sensing images was verified by comparing its results to the ground-measured yield. The results showed that the estimated yield of winter wheat based on remote sensing images is consistent with the ground-measured yield, with R2 of 0.56, RMSE of 1.22 t ha−1, and an average relative error of −6.01%. Based on time-series satellite remote sensing images, the improved CASA model can be used to estimate the NPP and thereby the yield of regional winter wheat. This approach satisfies the accuracy requirements for estimating regional winter wheat yield and thus may be used in actual applications. It also provides a technical reference for estimating large-scale crop yield.

Download Full-text

Winter Wheat Yield Prediction Using Convolutional Neural Networks from Environmental and Phenological Data

10.21203/rs.3.rs-789462/v1 ◽

2021 ◽

Author(s):

Amit Kumar Srivast ◽

Nima Safaei ◽

Saeed Khaki ◽

Gina Lopez ◽

Wenzhi Zeng ◽

...

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Deep Learning ◽

Winter Wheat ◽

Crop Yield ◽

Wheat Yield ◽

Yield Prediction ◽

Learning Models ◽

Winter Wheat Yield ◽

Machine Learning Models

Abstract Crop yield forecasting depends on many interactive factors including crop genotype, weather, soil, and management practices. This study analyzes the performance of machine learning and deep learning methods for winter wheat yield prediction using extensive datasets of weather, soil, and crop phenology. We propose a convolutional neural network (CNN) which uses the 1-dimentional convolution operation to capture the time dependencies of environmental variables. The proposed CNN, evaluated along with other machine learning models for winter wheat yield prediction in Germany, outperformed all other models tested. To address the seasonality, weekly features were used that explicitly take soil moisture and meteorological events into account. Our results indicated that nonlinear models such as deep learning models and XGboost are more effective in finding the functional relationship between the crop yield and input data compared to linear models and deep neural networks had a higher prediction accuracy than XGboost. One of the main limitations of machine learning models is their black box property. Therefore, we moved beyond prediction and performed feature selection, as it provides key results towards explaining yield prediction (variable importance by time). As such, our study indicates which variables have the most significant effect on winter wheat yield.

Download Full-text

Identifying the impact of multi-hazards on crop yield—A case for heat stress and dry stress on winter wheat yield in northern China

European Journal of Agronomy ◽

10.1016/j.eja.2015.10.009 ◽

2016 ◽

Vol 73 ◽

pp. 55-63 ◽

Cited By ~ 19

Author(s):

Yi Chen ◽

Zhao Zhang ◽

Pin Wang ◽

Xiao Song ◽

Xing Wei ◽

...

Keyword(s):

Heat Stress ◽

Winter Wheat ◽

Crop Yield ◽

Wheat Yield ◽

Northern China ◽

Winter Wheat Yield ◽

The Impact

Download Full-text

Estimating Farm Wheat Yields from NDVI and Meteorological Data

Agronomy ◽

10.3390/agronomy11050946 ◽

2021 ◽

Vol 11 (5) ◽

pp. 946

Author(s):

Astrid Vannoppen ◽

Anne Gobin

Keyword(s):

Winter Wheat ◽

Crop Yield ◽

Meteorological Data ◽

Wheat Yield ◽

Model Performance ◽

Weather Conditions ◽

Current Data ◽

Monthly Precipitation ◽

Empirical Modelling ◽

Winter Wheat Yield

Information on crop yield at scales ranging from the field to the global level is imperative for farmers and decision makers. The current data sources to monitor crop yield, such as regional agriculture statistics, are often lacking in spatial and temporal resolution. Remotely sensed vegetation indices (VIs) such as NDVI are able to assess crop yield using empirical modelling strategies. Empirical NDVI-based crop yield models were evaluated by comparing the model performance with similar models used in different regions. The integral NDVI and the peak NDVI were weak predictors of winter wheat yield in northern Belgium. Winter wheat (Triticum aestivum) yield variability was better predicted by monthly precipitation during tillering and anthesis than by NDVI-derived yield proxies in the period from 2016 to 2018 (R2 = 0.66). The NDVI series were not sensitive enough to yield affecting weather conditions during important phenological stages such as tillering and anthesis and were weak predictors in empirical crop yield models. In conclusion, winter wheat yield modelling using NDVI-derived yield proxies as predictor variables is dependent on the environment.

Download Full-text

Climate change impacts on winter wheat yield change – which climatic parameters are crucial in Pannonian lowland?

The Journal of Agricultural Science ◽

10.1017/s0021859612000640 ◽

2012 ◽

Vol 151 (6) ◽

pp. 757-774 ◽

Cited By ~ 21

Author(s):

B. LALIC ◽

J. EITZINGER ◽

D. T. MIHAILOVIC ◽

S. THALER ◽

M. JANCIC

Keyword(s):

Climate Change ◽

Winter Wheat ◽

Water Deficit ◽

Crop Yield ◽

Wheat Yield ◽

Maximum Temperature ◽

Climatic Parameters ◽

Yield Change ◽

The Future ◽

Winter Wheat Yield

SUMMARYOne of the main problems in estimating the effects of climate change on crops is the identification of those factors limiting crop growth in a selected environment. Previous studies have indicated that considering simple trends of either precipitation or temperature for the coming decades is insufficient for estimating the climate impact on yield in the future. One reason for this insufficiency is that changes in weather extremes or seasonal weather patterns may have marked impacts.The present study focuses on identifying agroclimatic parameters that can identify the effects of climate change and variability on winter wheat yield change in the Pannonian lowland. The impacts of soil type under past and future climates as well as the effect of different CO2 concentrations on yield formation are also considered. The Vojvodina region was chosen for this case study because it is a representative part of the Pannonian lowland.Projections of the future climate were taken from the HadCM3, ECHAM5 and NCAR-PCM climate models with the SRES-A2 scenario for greenhouse gas (GHG) emissions for the 2040 and 2080 integration periods. To calibrate and validate the Met&Roll weather generator, four-variable weather data series (for six main climatic stations in the Vojvodina region) were analysed. The grain yield of winter wheat was calculated using the SIRIUS wheat model for three different CO2 concentrations (330, 550 and 1050 ppm) dependent on the integration period. To estimate the effects of climatic parameters on crop yield, the correlation coefficient between crop yield and agroclimatic indices was calculated using the AGRICLIM software. The present study shows that for all soil types, the following indices are the most important for winter wheat yields in this region: (i) the number of days with water and temperature stress, (ii) the accumulated precipitation, (iii) the actual evapotranspiration (ETa) and (iv) the water deficit during the growing season. The high positive correlations between yield and the ETa, accumulated precipitation and the ratio between the ETa and reference evapotranspiration (ETr) for the April–June period indicate that water is and will remain a major limiting factor for growing winter wheat in this region. Indices referring to negative impact on yield are (i) the number of days with a water deficit for the April–June period and (ii) the number of days with maximum temperature above 25 °C (summer days) and the number of days with maximum temperature above 30 °C (tropical days) in May and June. These indices can be seen as indicators of extreme weather events such as drought and heat waves.

Download Full-text

Prediction of Winter Wheat Yield Based on Multi-Source Data and Machine Learning in China

Remote Sensing ◽

10.3390/rs12020236 ◽

2020 ◽

Vol 12 (2) ◽

pp. 236 ◽

Cited By ~ 6

Author(s):

Jichong Han ◽

Zhao Zhang ◽

Juan Cao ◽

Yuchuan Luo ◽

Liangliang Zhang ◽

...

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Winter Wheat ◽

Crop Yield ◽

Wheat Yield ◽

Growth Period ◽

Yield Prediction ◽

Climate Data ◽

Source Data ◽

Winter Wheat Yield

Wheat is one of the main crops in China, and crop yield prediction is important for regional trade and national food security. There are increasing concerns with respect to how to integrate multi-source data and employ machine learning techniques to establish a simple, timely, and accurate crop yield prediction model at an administrative unit. Many previous studies were mainly focused on the whole crop growth period through expensive manual surveys, remote sensing, or climate data. However, the effect of selecting different time window on yield prediction was still unknown. Thus, we separated the whole growth period into four time windows and assessed their corresponding predictive ability by taking the major winter wheat production regions of China as an example in the study. Firstly we developed a modeling framework to integrate climate data, remote sensing data and soil data to predict winter wheat yield based on the Google Earth Engine (GEE) platform. The results show that the models can accurately predict yield 1~2 months before the harvesting dates at the county level in China with an R2 > 0.75 and yield error less than 10%. Support vector machine (SVM), Gaussian process regression (GPR), and random forest (RF) represent the top three best methods for predicting yields among the eight typical machine learning models tested in this study. In addition, we also found that different agricultural zones and temporal training settings affect prediction accuracy. The three models perform better as more winter wheat growing season information becomes available. Our findings highlight a potentially powerful tool to predict yield using multiple-source data and machine learning in other regions and for crops.

Download Full-text

Development of the methodology of estimating of agricultural crop yield potential with consideration of climate and agrophytotechnology impact

Ukrainian hydrometeorological journal ◽

10.31481/uhmj.20.2017.06 ◽

2017 ◽

pp. 52-60

Author(s):

V. P. Dmytrenko ◽

L. P. Odnolyetok ◽

О. О. Kryvoshein ◽

A. V. Krukivska

Keyword(s):

Winter Wheat ◽

Crop Yield ◽

Crop Yields ◽

Wheat Yield ◽

Yield Potential ◽

Agricultural Crop ◽

Yield Level ◽

Winter Wheat Yield ◽

The Mathematical Model

In the paper it is outlined the main methodological positions and the results of the approbation of new approaches to the integrated assessment of the potential of crop yields. There are considered the theoretical foundations of a joint assessment of the biological, ecological and anthropogenic components of the yield potential of agricultural crops which are based on the ecosystem concept and the mathematical model "Weather-Crop Yield" developed by V. P. Dmytrenko. In the considered approaches the peculiarities of the influence of various environmental factors on the formation of crop yields are determined by indicators of various potential yields - general, climatic and trend (agrotechnological). Each type of yield potential can be used for evaluation of the effectiveness of the conditions of field crop growing for each factor taken into account, as well as the optimality criterion in the agrometeorological adaptation strategies and also as a criterion for the degree of sensitivity of the yield level to the conditions of crops cultivating. The developed approaches are tested on the example of estimation of long-term dynamics of winter wheat yield potential in Ukraine. According to the results of the evaluation of different factors of the potential of the productivity of winter wheat for the periods 1961-1990 and 1991-2010 the dominant importance of organizational and technological processes in comparison with the contribution of changes of agroclimatic conditions has been determined in both periods.

Download Full-text

Hardpan Location and Crop Yield: From Information to Precision Tillage Map

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.1059.27 ◽

2014 ◽

Vol 1059 ◽

pp. 27-33

Author(s):

Katarína Kollárová ◽

Miroslav Žitňák ◽

Maroš Korenko

Keyword(s):

Winter Wheat ◽

Spatial Variability ◽

Crop Yield ◽

Field Experiments ◽

Wheat Yield ◽

Experiment Design ◽

Winter Wheat Yield

This paper explores the incidence of hardpans in a field of 14.27 ha. Emphasis is placed on winter wheat yield and its comparison with hardpan location. The objective of this study was to determine prescriptions of different tillage depths for a precision tillage map. In order to meet the above objectives, laboratory and field experiments were conducted based on the experiment design with 60 monitoring points. The results of experiments confirmed the within-field spatial variability of hardpans and crop yield and revealed areas where yield is influenced by detrimental compaction.

Download Full-text