Winter Wheat Yield Prediction at County Level and Uncertainty Analysis in Main Wheat-Producing Regions of China with Deep Learning Approaches

Timely and accurate forecasting of crop yields is crucial to food security and sustainable development in the agricultural sector. However, winter wheat yield estimation and forecasting on a regional scale still remains challenging. In this study, we established a two-branch deep learning model to predict winter wheat yield in the main producing regions of China at the county level. The first branch of the model was constructed based on the Long Short-Term Memory (LSTM) networks with inputs from meteorological and remote sensing data. Another branch was constructed using Convolution Neural Networks (CNN) to model static soil features. The model was then trained using the detrended statistical yield data during 1982 to 2015 and evaluated by leave-one-year-out-validation. The evaluation results showed a promising performance of the model with the overall R 2 and RMSE of 0.77 and 721 kg/ha, respectively. We further conducted yield prediction and uncertainty analysis based on the two-branch model and obtained the forecast accuracy in one month prior to harvest of 0.75 and 732 kg/ha. Results also showed that while yield detrending could potentially introduce higher uncertainty, it had the advantage of improving the model performance in yield prediction.

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

Combined Use of Landsat-8 and Sentinel-2A Images for Winter Crop Mapping and Winter Wheat Yield Assessment at Regional Scale

AIMS Geosciences ◽

10.3934/geosci.2017.2.163 ◽

2017 ◽

Vol 3 (2) ◽

pp. 163-186 ◽

Cited By ~ 38

Author(s):

Sergii Skakun ◽

◽

Eric Vermote ◽

Jean-Claude Roger ◽

Belen Franch ◽

...

Keyword(s):

Winter Wheat ◽

Regional Scale ◽

Wheat Yield ◽

Landsat 8 ◽

Combined Use ◽

Winter Crop ◽

Winter Wheat Yield ◽

Crop Mapping ◽

Sentinel 2A

Download Full-text

RiceSAP: An Efficient Satellite-Based AquaCrop Platform for Rice Crop Monitoring and Yield Prediction on a Farm- to Regional-Scale

Agronomy ◽

10.3390/agronomy10060858 ◽

2020 ◽

Vol 10 (6) ◽

pp. 858 ◽

Cited By ~ 1

Author(s):

Watcharee Veerakachen ◽

Mongkol Raksapatcharawong

Keyword(s):

Climate Change ◽

Agricultural Sector ◽

Crop Yields ◽

Regional Scale ◽

Processing System ◽

Mobile App ◽

Percentage Error ◽

Yield Prediction ◽

Crop Monitoring ◽

The Impact

Advanced technologies in the agricultural sector have been adopted as global trends in response to the impact of climate change on food sustainability. An ability to monitor and predict crop yields is imperative for effective agronomic decision making and better crop management. This work proposes RiceSAP, a satellite-based AquaCrop processing system for rice whose climatic input is derived from TERRA/MODIS-LST and FY-2/IR-rainfall products to provide crop monitoring and yield prediction services at regional-scale with no need for weather station. The yield prediction accuracy is significantly improved by our proposed recalibration algorithm on the simulated canopy cover (CC) using Sentinel-2 NDVI product. A developed mobile app provides an intuitive interface for collecting farm-scale inputs and providing timely feedbacks to farmers to make informed decisions. We show that RiceSAP could predict yields 2 months before harvest with a mean absolute percentage error (MAPE) of 14.8%, in the experimental field. Further experiments on randomly selected 20 plots with various soil series showed comparable results with an average MAPE of 16.7%. Thus, this work is potentially applicable countrywide; and can be beneficial to all stakeholders in the entire rice supply chain for effective adaptation to climate change.

Download Full-text

Identifying the Contributions of Multi-Source Data for Winter Wheat Yield Prediction in China

Remote Sensing ◽

10.3390/rs12050750 ◽

2020 ◽

Vol 12 (5) ◽

pp. 750 ◽

Cited By ~ 3

Author(s):

Juan Cao ◽

Zhao Zhang ◽

Fulu Tao ◽

Liangliang Zhang ◽

Yuchuan Luo ◽

...

Keyword(s):

Winter Wheat ◽

Satellite Data ◽

Large Scale ◽

Wheat Yield ◽

Yield Variability ◽

Yield Prediction ◽

Climate Data ◽

Light Gradient ◽

Source Data ◽

Winter Wheat Yield

Wheat is a leading cereal grain throughout the world. Timely and reliable wheat yield prediction at a large scale is essential for the agricultural supply chain and global food security, especially in China as an important wheat producing and consuming country. The conventional approach using either climate or satellite data or both to build empirical and crop models has prevailed for decades. However, to what extent climate and satellite data can improve yield prediction is still unknown. In addition, socio-economic (SC) factors may also improve crop yield prediction, but their contributions need in-depth investigation, especially in regions with good irrigation conditions, sufficient fertilization, and pesticide application. Here, we performed the first attempt to predict wheat yield across China from 2001 to 2015 at the county-level by integrating multi-source data, including monthly climate data, satellite data (i.e., Vegetation indices (VIs)), and SC factors. The results show that incorporating all the datasets by using three machine learning methods (Ridge Regression (RR), Random Forest (RF), and Light Gradient Boosting (LightGBM)) can achieve the best performance in yield prediction (R2: 0.68~0.75), with the most individual contributions from climate (~0.53), followed by VIs (~0.45), and SC factors (~0.30). In addition, the combinations of VIs and climate data can capture inter-annual yield variability more effectively than other combinations (e.g., combinations of climate and SC, and combinations of VIs and SC), while combining SC with climate data can better capture spatial yield variability than others. Climate data can provide extra and unique information across the entire growing season, while the peak stage of VIs (Mar.~Apr.) do so. Furthermore, incorporating spatial information and soil proprieties into the benchmark models can improve wheat yield prediction by 0.06 and 0.12, respectively. The optimal wheat prediction can be achieved with approximately a two-month leading time before maturity. Our study develops timely and robust methods for winter wheat yield prediction at a large scale in China, which can be applied to other crops and regions.

Download Full-text

Sensitivity analysis of the Aquacrop and SAFYE crop models for the assessment of water limited winter wheat yield in regional scale applications

PLoS ONE ◽

10.1371/journal.pone.0187485 ◽

2017 ◽

Vol 12 (11) ◽

pp. e0187485 ◽

Cited By ~ 16

Author(s):

Paolo Cosmo Silvestro ◽

Stefano Pignatti ◽

Hao Yang ◽

Guijun Yang ◽

Simone Pascucci ◽

...

Keyword(s):

Sensitivity Analysis ◽

Winter Wheat ◽

Regional Scale ◽

Wheat Yield ◽

Crop Models ◽

Winter Wheat Yield

Download Full-text

Prior Season Crop Type Masks for Winter Wheat Yield Forecasting: A US Case Study

Remote Sensing ◽

10.3390/rs10101659 ◽

2018 ◽

Vol 10 (10) ◽

pp. 1659 ◽

Cited By ~ 4

Author(s):

Inbal Becker-Reshef ◽

Belen Franch ◽

Brian Barker ◽

Emilie Murphy ◽

Andres Santamaria-Artigas ◽

...

Keyword(s):

Time Series ◽

Winter Wheat ◽

Spatial Resolution ◽

Vegetation Index ◽

Time Series Data ◽

Crop Yields ◽

Wheat Yield ◽

Series Data ◽

Crop Type ◽

Winter Wheat Yield

Monitoring and forecasting crop yields is a critical component of understanding and better addressing global food security challenges. Detailed spatial information on crop-type distribution is fundamental for in-season crop condition monitoring and yields forecasting over large agricultural areas, as it enables the extraction of crop-specific signals. Yet, the availability of such data within the growing season is often limited. Within this context, this study seeks to develop a practical approach to extract a crop-specific signal for yield forecasting in cases where crop rotations are prevalent, and detailed in-season information on crop type distribution is not available. We investigated the possibility of accurately forecasting winter wheat yields by using a counter-intuitive approach, which coarsens the spatial resolution of out-of-date detailed winter wheat masks and uses them in combination with easily accessibly coarse spatial resolution remotely sensed time series data. The main idea is to explore an optimal spatial resolution at which crop type changes will be negligible due to crop rotation (so a previous seasons’ mask, which is more readily available can be used) and an informative signal can be extracted, so it can be correlated to crop yields. The study was carried out in the United States of America (USA) and utilized multiple years of NASA Moderate Resolution Imaging Spectroradiometer (MODIS) data, US Department of Agriculture (USDA) National Agricultural Statistics Service (NASS) detailed wheat masks, and a regression-based winter wheat yield model. The results indicate that, in places where crop rotations were prevalent, coarsening the spatial scale of a crop type mask from the previous season resulted in a constant per-pixel wheat proportion over multiple seasons. This enables the consistent extraction of a crop-specific vegetation index time series that can be used for in-season monitoring and yield estimation over multiple years using a single mask. In the case of the USA, using a moderate resolution crop type mask from a previous season aggregated to 5 km resolution, resulted in a 0.7% tradeoff in accuracy relative to the control case where annually-updated detailed crop-type masks were available. These findings suggest that when detailed in-season data is not available, winter wheat yield can be accurately forecasted (within 10%) prior to harvest using a single, prior season crop mask and coarse resolution Normalized Difference Vegetation Index (NDVI) time series data.

Download Full-text

Possible Scenarios of Winter Wheat Yield Reduction of Dryland Qazvin Province, Iran, Based on Prediction of Temperature and Precipitation Till the End of the Century

Climate ◽

10.3390/cli6040078 ◽

2018 ◽

Vol 6 (4) ◽

pp. 78 ◽

Cited By ~ 4

Author(s):

Behnam Mirgol ◽

Meisam Nazari

Keyword(s):

Winter Wheat ◽

Crop Yields ◽

Wheat Yield ◽

Annual Precipitation ◽

Yield Reduction ◽

Factors Affecting ◽

Temperature And Precipitation ◽

Mean Temperature ◽

Winter Wheat Yield ◽

Semi Arid

The climate of the Earth is changing. The Earth’s temperature is projected to maintain its upward trend in the next few decades. Temperature and precipitation are two very important factors affecting crop yields, especially in arid and semi-arid regions. There is a need for future climate predictions to protect vulnerable sectors like agriculture in drylands. In this study, the downscaling of two important climatic variables—temperature and precipitation—was done by the CanESM2 and HadCM3 models under five different scenarios for the semi-arid province of Qazvin, located in Iran. The most efficient scenario was selected to predict the dryland winter wheat yield of the province for the three periods: 2010–2039, 2040–2069, and 2070–2099. The results showed that the models are able to satisfactorily predict the daily mean temperature and annual precipitation for the three mentioned periods. Generally, the daily mean temperature and annual precipitation tended to decrease in these periods when compared to the current reference values. However, the scenarios rcp2.6 and B2, respectively, predicted that the precipitation will fall less or even increase in the period 2070–2099. The scenario rcp2.6 seemed to be the most efficient to predict the dryland winter wheat yield of the province for the next few decades. The grain yield is projected to drop considerably over the three periods, especially in the last period, mainly due to the reduction in precipitation in March. This leads us to devise some adaptive strategies to prevent the detrimental impacts of climate change on the dryland winter wheat yield of the province.

Download Full-text

Geographically and temporally weighted neural network for winter wheat yield prediction

Remote Sensing of Environment ◽

10.1016/j.rse.2021.112514 ◽

2021 ◽

Vol 262 ◽

pp. 112514

Author(s):

Luwei Feng ◽

Yumiao Wang ◽

Zhou Zhang ◽

Qingyun Du

Keyword(s):

Neural Network ◽

Winter Wheat ◽

Wheat Yield ◽

Yield Prediction ◽

Winter Wheat Yield

Download Full-text

The effect of soil and weather conditions on yields of winter wheat in multi-environmental trials

Biometrical Letters ◽

10.2478/bile-2019-0016 ◽

2019 ◽

Vol 56 (2) ◽

pp. 263-279 ◽

Cited By ~ 1

Author(s):

Marzena Iwańska ◽

Michał Stępień

Keyword(s):

Winter Wheat ◽

Crop Yields ◽

Wheat Yield ◽

Weather Conditions ◽

Grain Filling ◽

Growth Stages ◽

Yield Data ◽

Winter Wheat Yield ◽

Crop Growth Stage ◽

The Impact

SummaryDrought reduces crop yields not only in areas of arid climate. The impact of droughts depends on the crop growth stage and soil properties. The frequency of droughts will increase due to climate change. It is important to determine the environmental variables that have the strongest effect on wheat yields in dry years. The effect of soil and weather on wheat yield was evaluated in 2018, which was considered a very dry year in Europe. The winter wheat yield data from 19 trial locations of the Research Center of Cultivar Testing (COBORU), Poland, were used. Soil data from the trial locations, mean air temperature (T) and precipitation (P) were considered as environmental factors, as well as the climatic water balance (CWB). The hydrothermal coefficient (HTC), which is based on P and T, was also used. The effect of these factors on winter wheat yield was related to the weather conditions at particular growth stages. The soil had a greater effect than the weather conditions. CWB, P, T and HTC showed a clear relationship with winter wheat yield. Soil data and HTC are the factors most recommended for models predicting crop yields. In the selection of drought-tolerant genotypes, the plants should be subjected to stress especially during the heading and grain filling growth stages.

Download Full-text

Combined Impact of Climate Change and Land Qualities on Winter Wheat Yield in Central Fore-Caucasus: The Long-Term Retrospective Study

Land ◽

10.3390/land10121339 ◽

2021 ◽

Vol 10 (12) ◽

pp. 1339

Author(s):

Vasilii Erokhin ◽

Alexander Esaulko ◽

Elena Pismennaya ◽

Evgeny Golosnoy ◽

Olga Vlasova ◽

...

Keyword(s):

Climate Change ◽

Winter Wheat ◽

Agricultural Sector ◽

Crop Yields ◽

Climatic Factors ◽

Wheat Yield ◽

Climate Impacts ◽

Contributing Factors ◽

Support Tool

Progressing climate change has been increasingly threatening the agricultural sector by compromising the resilience of ecosystems and endangering food security worldwide. Altering patterns of major climatic parameters require the perspectives of agricultural production to be assessed in a holistic way to understand the interactions of climatic and non-climatic factors on crop yield. However, it is difficult to distinguish the direct influence of changing temperature and precipitation on the productivity of crops while simultaneously capturing other contributing factors, such as spatial allocation of agricultural lands, economic conditions of land use, and soil fertility. Wide temporal and spatial fluctuations of climatic impacts substantially complicate the task. In the case of the 170-year retrospective analysis of the winter wheat sector in the south of Russia, this study tackles the challenge by establishing the multiplicative function to estimate crop yields as a long-term result of a combined influence of agricultural output parameters, qualities of soils, and climate variables. It is found that within the climate–land–yield triangle, linkages tighten or weaken depending on the strength of noise effects of economic and social perturbations. Still, the overall pressure of climate change on the cultivation of winter wheat has been aggravating. The inter-territory relocation of areas under crops based on the matching of soil types, precipitation, air temperature, and erodibility of lands is suggested as a climate response option. The approach can be employed as a decision support tool when developing territory-specific land management policies to cope with adverse climate impacts on the winter wheat sector.

Download Full-text