Abstract
Crop yield must increase to keep pace with growing global demand. Past increases in crop production have rarely been attributable to an individual innovation but have occurred when ...technologies and practices combine to form improved farming systems. Inevitably this has involved synergy between genotypic and management improvements. We argue that research focused on developing synergistic systems that overcome clear production constraints will accelerate increases in yield. This offers the opportunity to better focus and multiply the impact of discipline-focused research. Here we use the rainfed grain production systems of south-eastern Australia as a case study of how transformational change in water productivity can be achieved with research focused on genotype × management synergies. In this region, rainfall is low and variable and has declined since 1990. Despite this, growers have maintained yields by implementing synergistic systems combining innovations in (i) soil water conservation, (ii) crop diversity, (iii) earlier sowing, and (iv) matching nitrogen fertilizer to water-limited demand. Further increases are emerging from synergies between genetic improvements to deliver flowering time stability, adjusted sowing times, and potential dual-purpose use. Collaboration between agronomists, physiologists, and crop breeders has led to development of commercial genotypes with stable flowering time that are in early phases of testing and adoption.
Many studies have applied machine learning to crop yield prediction with a focus on specific case studies. The data and methods they used may not be transferable to other crops and locations. On the ...other hand, operational large-scale systems, such as the European Commission's MARS Crop Yield Forecasting System (MCYFS), do not use machine learning. Machine learning is a promising method especially when large amounts of data are being collected and published. We combined agronomic principles of crop modeling with machine learning to build a machine learning baseline for large-scale crop yield forecasting. The baseline is a workflow emphasizing correctness, modularity and reusability. For correctness, we focused on designing explainable predictors or features (in relation to crop growth and development) and applying machine learning without information leakage. We created features using crop simulation outputs and weather, remote sensing and soil data from the MCYFS database. We emphasized a modular and reusable workflow to support different crops and countries with small configuration changes. The workflow can be used to run repeatable experiments (e.g. early season or end of season predictions) using standard input data to obtain reproducible results. The results serve as a starting point for further optimizations. In our case studies, we predicted yield at regional level for five crops (soft wheat, spring barley, sunflower, sugar beet, potatoes) and three countries (the Netherlands (NL), Germany (DE), France (FR)). We compared the performance with a simple method with no prediction skill, which either predicted a linear yield trend or the average of the training set. We also aggregated the predictions to the national level and compared with past MCYFS forecasts. The normalized RMSE (NRMSE) for early season predictions (30 days after planting) were comparable for NL (all crops), DE (all except soft wheat) and FR (soft wheat, spring barley, sunflower). For example, NRMSE was 7.87 for soft wheat (NL) (6.32 for MCYFS) and 8.21 for sugar beet (DE) (8.79 for MCYFS). In contrast, NRMSEs for soft wheat (DE), sugar beet (FR) and potatoes (FR) were twice as much compared to MCYFS. NRMSEs for end of season were still comparable to MCYFS for NL, but worse for DE and FR. The baseline can be improved by adding new data sources, designing more predictive features and evaluating different machine learning algorithms. The baseline will motivate the use of machine learning in large-scale crop yield forecasting.
•Combined principles of crop modeling with machine learning for crop yield forecasting•Designed a generic workflow emphasizing correctness, modularity and reusability•Useful to explore benefits of machine learning in large-scale crop yield forecasting•Tested the workflow by predicting regional crop yields for 3 countries and 5 crops•Early season predictions were comparable with the MARS Crop Yield Forecasting System
•Machine learning (ML)-based crop yield prediction papers have been synthesized.•We selected 50 ML-based papers and later, 30 deep learning-based papers.•Most used features are temperature, rainfall, ...and soil type.•The most widely used ML algorithm is Neural Networks.•The most widely used deep learning algorithm is CNN.
Machine learning is an important decision support tool for crop yield prediction, including supporting decisions on what crops to grow and what to do during the growing season of the crops. Several machine learning algorithms have been applied to support crop yield prediction research. In this study, we performed a Systematic Literature Review (SLR) to extract and synthesize the algorithms and features that have been used in crop yield prediction studies. Based on our search criteria, we retrieved 567 relevant studies from six electronic databases, of which we have selected 50 studies for further analysis using inclusion and exclusion criteria. We investigated these selected studies carefully, analyzed the methods and features used, and provided suggestions for further research. According to our analysis, the most used features are temperature, rainfall, and soil type, and the most applied algorithm is Artificial Neural Networks in these models. After this observation based on the analysis of machine learning-based 50 papers, we performed an additional search in electronic databases to identify deep learning-based studies, reached 30 deep learning-based papers, and extracted the applied deep learning algorithms. According to this additional analysis, Convolutional Neural Networks (CNN) is the most widely used deep learning algorithm in these studies, and the other widely used deep learning algorithms are Long-Short Term Memory (LSTM) and Deep Neural Networks (DNN).
Agriculture provides humanity with food, fibers, fuel, and raw materials that are paramount for human livelihood. Today, this role must be satisfied within a context of environmental sustainability ...and climate change, combined with an unprecedented and still-expanding human population size, while maintaining the viability of agricultural activities to ensure both subsistence and livelihoods. Remote sensing has the capacity to assist the adaptive evolution of agricultural practices in order to face this major challenge, by providing repetitive information on crop status throughout the season at different scales and for different actors. We start this review by making an overview of the current remote sensing techniques relevant for the agricultural context. We present the agronomical variables and plant traits that can be estimated by remote sensing, and we describe the empirical and deterministic approaches to retrieve them. A second part of this review illustrates recent research developments that permit to strengthen applicative capabilities in remote sensing according to specific requirements for different types of stakeholders. Such agricultural applications include crop breeding, agricultural land use monitoring, crop yield forecasting, as well as ecosystem services in relation to soil and water resources or biodiversity loss. Finally, we provide a synthesis of the emerging opportunities that should strengthen the role of remote sensing in providing operational, efficient and long-term services for agricultural applications.
•We make a review of agronomical variables and plant traits that can be estimated from remote sensing.•We describe different methodological approaches to retrieve them.•We discuss how these variables are employed by different stakeholders for specific applications.•We conclude with an overview of caveats and future challenges.
Crop yield forecasting at national level relies on predictors aggregated from smaller spatial units to larger ones according to harvested crop areas. Such crop areas come from land cover maps or ...reported statistics, both of which can have errors and uncertainties. Sub-national or regional crop yield forecasting minimizes the propagation of these errors to some extent. In addition, regional forecasts provide added value and insights to stakeholders on regional differences within a country, which would otherwise compensate each other at national level. We propose a crop yield forecasting approach for multiple spatial levels based on regional crop yield forecasts from machine learning. Machine learning, with its data-driven approach, can leverage larger data sizes and capture nonlinear relationships between predictors and yield at regional level. We designed a generic machine learning workflow to demonstrate the benefits of regional crop yield forecasting in Europe. To evaluate the quality and usefulness of regional forecasts, we predicted crop yields for 35 case studies, including nine countries that are major producers of six crops (soft wheat, spring barley, sunflower, grain maize, sugar beets and potatoes). Machine learning models at regional level had lower normalized root mean squared errors (NRMSE) and uncertainty than a linear trend model, with Wilcoxon p-values of 3e-7 and 2e-7 for 60 days before harvest and end of season respectively. Similarly, regional machine learning forecasts aggregated to national level had lower NRMSEs than forecasts from an operational system in 18 out of 35 cases 60 days before harvest, with a Wilcoxon p-value of 0.95 indicating similar performance. Our models have room for improvement, especially during extreme years. Nevertheless, regional crop yield forecasts from machine learning and aggregated national forecasts provide a consistent forecasting method across spatial levels and insights from regional differences to support important policy decisions.
•Crop yield forecasts for multiple spatial levels using machine learning.•Evaluated machine learning on 35 case studies covering nine countries and six crops.•Regional forecasts had lower errors and uncertainty than trend forecasts.•Forecasts captured spatial patterns quite well for average but not extreme harvests.•Aggregated national forecasts were comparable to the European MARS System forecasts.
•The CNNs are able to reduce crop yield prediction uncertainty considerably.•RGB images perform better over NDVI images.•Sufficient network depth with regularization were required for better ...performance.
Using remote sensing and UAVs in smart farming is gaining momentum worldwide. The main objectives are crop and weed detection, biomass evaluation and yield prediction. Evaluating machine learning methods for remote sensing based yield prediction requires availability of yield mapping devices, which are still not very common among farmers. In this study Convolutional Neural Networks (CNNs) – a deep learning methodology showing outstanding performance in image classification tasks – are applied to build a model for crop yield prediction based on NDVI and RGB data acquired from UAVs. The effect of various aspects of the CNN such as selection of the training algorithm, depth of the network, regularization strategy, and tuning of the hyperparameters on the prediction efficiency are tested. Using the Adadelta training algorithm, L2 regularization with early stopping and a CNN with 6 convolutional layers, mean absolute error (MAE) in yield prediction of 484.3 kg/ha and mean absolute percentage error (MAPE) of 8.8% was achieved for data acquired during the early period of the growth season (i.e., in June of 2017, growth phase <25%) with RGB data. When using data acquired later in July and August of 2017 (growth phase >25%), MAE of 624.3 kg/ha (MAPE: 12.6%) was obtained. Significantly, the CNN architecture performed better with RGB data than the NDVI data.
Abstract When sowing any agricultural crop, a number of requirements must be observed. One of these requirements is the right sowing time, because it has a great influence on the quality and quantity ...of the crop. In this study, using the example of Sarepta mustard, the influence of the sowing time on the yield of agricultural crops was revealed.
•A Combined Convolutional Neural Network for crop yield forecasting is presented.•The effect of using Convolutional LSTM is explored for crop yield forecasting.•The proposed models was compared ...against the competing approaches.
Crop yield forecasting is of great importance to crop market planning, crop insurance, harvest management, and optimal nutrient management. Commonly used approaches for crop prediction include but are not limited to conducting extensive manual surveys or using data from remote sensing. Considering the increasing amount of data provided by remote sensing imagery, this approach is becoming increasingly important for the task of crop yield forecasting and there is a need for more sophisticated approaches to extract the inherent spatiotemporal patterns of these data. Although considerable progress has been made in this field by using Deep Learning (DL) methods such as Convolutional Neural Networks (CNN), no study before has investigated the use of Convolutional Long Short-Term Memory (ConvLSTM) for crop yield forecasting. Here, we propose DeepYield, a combined structure, that integrates the ConvLSTM layers with the 3-Dimensional CNN (3DCNN) for more accurate and reliable spatiotemporal feature extraction. The models are trained by using county-based historical yield data and MODIS Land Surface Temperature (LST), Surface Reflectance (SR), and Land Cover (LC) data over 1836 primary soybean growing counites in the Contiguous United States (CONUS). The forecasting performance of the developed models is compared against the competing approaches including Decision Trees, CNN + GP, and CNN-LSTM and results indicate that DeepYield significantly outperforms these techniques and also performs better than both ConvLSTM and 3DCNN.