Explore the vast range of titles available.

The current trajectory for crop yields is insufficient to nourish the world’s population by 2050 1 . Greater and more consistent crop production must be achieved against a backdrop of climatic stress that limits yields, owing to shifts in pests and pathogens, precipitation, heat-waves and other weather extremes. Here we consider the potential of plant sciences to address post-Green Revolution challenges in agriculture and explore emerging strategies for enhancing sustainable crop production and resilience in a changing climate. Accelerated crop improvement must leverage naturally evolved traits and transformative engineering driven by mechanistic understanding, to yield the resilient production systems that are needed to ensure future harvests. Genetic strategies for improving the yield and sustainability of agricultural crops, and the resilience of crops in the face of biotic and abiotic stresses contingent on projected climate change, are evaluated.

Background The study focuses on enhancing the effectiveness of precision agriculture through the application of deep learning technologies. Precision agriculture, which aims to optimize farming practices by monitoring and adjusting various factors influencing crop growth, can greatly benefit from artificial intelligence (AI) methods like deep learning. The Agro Deep Learning Framework (ADLF) was developed to tackle critical issues in crop cultivation by processing vast datasets. These datasets include variables such as soil moisture, temperature, and humidity, all of which are essential to understanding and predicting crop behavior. By leveraging deep learning models, the framework seeks to improve decision-making processes, detect potential crop problems early, and boost agricultural productivity. Results The study found that the Agro Deep Learning Framework (ADLF) achieved an accuracy of 85.41%, precision of 84.87%, recall of 84.24%, and an F1-Score of 88.91%, indicating strong predictive capabilities for improving crop management. The false negative rate was 91.17% and the false positive rate was 89.82%, highlighting the framework's ability to correctly detect issues while minimizing errors. These results suggest that ADLF can significantly enhance decision-making in precision agriculture, leading to improved crop yield and reduced agricultural losses. Conclusions The ADLF can significantly improve precision agriculture by leveraging deep learning to process complex datasets and provide valuable insights into crop management. The framework allows farmers to detect issues early, optimize resource use, and improve yields. The study demonstrates that AI-driven agriculture has the potential to revolutionize farming, making it more efficient and sustainable. Future research could focus on further refining the model and exploring its applicability across different types of crops and farming environments.

Several studies have shown that global crop production needs to double by 2050 to meet the projected demands from rising population, diet shifts, and increasing biofuels consumption. Boosting crop yields to meet these rising demands, rather than clearing more land for agriculture has been highlighted as a preferred solution to meet this goal. However, we first need to understand how crop yields are changing globally, and whether we are on track to double production by 2050. Using ∼2.5 million agricultural statistics, collected for ∼13,500 political units across the world, we track four key global crops-maize, rice, wheat, and soybean-that currently produce nearly two-thirds of global agricultural calories. We find that yields in these top four crops are increasing at 1.6%, 1.0%, 0.9%, and 1.3% per year, non-compounding rates, respectively, which is less than the 2.4% per year rate required to double global production by 2050. At these rates global production in these crops would increase by ∼67%, ∼42%, ∼38%, and ∼55%, respectively, which is far below what is needed to meet projected demands in 2050. We present detailed maps to identify where rates must be increased to boost crop production and meet rising demands.

Crop yield prediction is extremely challenging due to its dependence on multiple factors such as crop genotype, environmental factors, management practices, and their interactions. This paper presents a deep learning framework using convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for crop yield prediction based on environmental data and management practices. The proposed CNN-RNN model, along with other popular methods such as random forest (RF), deep fully connected neural networks (DFNN), and LASSO, was used to forecast corn and soybean yield across the entire Corn Belt (including 13 states) in the United States for years 2016, 2017, and 2018 using historical data. The new model achieved a root-mean-square-error (RMSE) 9% and 8% of their respective average yields, substantially outperforming all other methods that were tested. The CNN-RNN has three salient features that make it a potentially useful method for other crop yield prediction studies. (1) The CNN-RNN model was designed to capture the time dependencies of environmental factors and the genetic improvement of seeds over time without having their genotype information. (2) The model demonstrated the capability to generalize the yield prediction to untested environments without significant drop in the prediction accuracy. (3) Coupled with the backpropagation method, the model could reveal the extent to which weather conditions, accuracy of weather predictions, soil conditions, and management practices were able to explain the variation in the crop yields.

Deep learning has emerged as a potential tool for crop yield prediction, allowing the model to automatically extract features and learn from the datasets. Meanwhile, smart farming technology enables the farmers to achieve maximum crop yield by extracting essential parameters of crop growth. This systematic literature review highlights the existing research gaps in a particular area of deep learning methodologies and guides us in analyzing the impact of vegetation indices and environmental factors on crop yield. To achieve the aims of this study, prior studies from 2012 to 2022 from various databases are collected and analyzed. The study focuses on the advantages of using deep learning in crop yield prediction, the suitable remote sensing technology based on the data acquisition requirements, and the various features that influence crop yield prediction. This study finds that Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) are the most widely used deep learning approaches for crop yield prediction. The commonly used remote sensing technology is satellite remote sensing technology—in particular, the use of the Moderate-Resolution Imaging Spectroradiometer (MODIS). Findings show that vegetation indices are the most used feature for crop yield prediction. However, it is also observed that the most used features in the literature do not always work for all the approaches. The main challenges of using deep learning approaches and remote sensing for crop yield prediction are how to improve the working model for better accuracy, the practical implication of the model for providing accurate information about crop yield to agriculturalists, growers, and policymakers, and the issue with the black box property.

To keep up with the growth of human population and to circumvent deleterious effects of global climate change, it is essential to enhance crop yield to achieve higher production. Here we review mathematical models of oxygenic photosynthesis that are extensively used, and discuss in depth a subset that accounts for diverse approaches providing solutions to our objective. These include models (1) to study different ways to enhance photosynthesis, such as fine-tuning antenna size, photoprotection and electron transport; (2) to bioengineer carbon metabolism; and (3) to evaluate the interactions between the process of photosynthesis and the seasonal crop dynamics, or those that have included statistical whole-genome prediction methods to quantify the impact of photosynthesis traits on the improvement of crop yield. We conclude by emphasizing that the results obtained in these studies clearly demonstrate that mathematical modelling is a key tool to examine different approaches to improve photosynthesis for better productivity, while effective multiscale crop models, especially those that also include remote sensing data, are indispensable to verify different strategies to obtain maximized crop yields.

Reliable and timely crop-yield prediction and crop mapping are crucial for food security and decision making in the food industry and in agro-environmental management. The global coverage, rich spectral and spatial information and repetitive nature of remote sensing (RS) data have made them effective tools for mapping crop extent and predicting yield before harvesting. Advanced machine-learning methods, particularly deep learning (DL), can accurately represent the complex features essential for crop mapping and yield predictions by accounting for the nonlinear relationships between variables. The DL algorithm has attained remarkable success in different fields of RS and its use in crop monitoring is also increasing. Although a few reviews cover the use of DL techniques in broader RS and agricultural applications, only a small number of references are made to RS-based crop-mapping and yield-prediction studies. A few recently conducted reviews attempted to provide overviews of the applications of DL in crop-yield prediction. However, they did not cover crop mapping and did not consider some of the critical attributes that reveal the essential issues in the field. This study is one of the first in the literature to provide a thorough systematic review of the important scientific works related to state-of-the-art DL techniques and RS in crop mapping and yield estimation. This review systematically identified 90 papers from databases of peer-reviewed scientific publications and comprehensively reviewed the aspects related to the employed platforms, sensors, input features, architectures, frameworks, training data, spatial distributions of study sites, output scales, evaluation metrics and performances. The review suggests that multiple DL-based solutions using different RS data and DL architectures have been developed in recent years, thereby providing reliable solutions for crop mapping and yield prediction. However, challenges related to scarce training data, the development of effective, efficient and generalisable models and the transparency of predictions should be addressed to implement these solutions at scale for diverse locations and crops.

The potential impacts of climate change on crop productivity are of widespread interest to those concerned with addressing climate change and improving global food security. Two common approaches to assess these impacts are process-based simulation models, which attempt to represent key dynamic processes affecting crop yields, and statistical models, which estimate functional relationships between historical observations of weather and yields. Examples of both approaches are increasingly found in the scientific literature, although often published in different disciplinary journals. Here we compare published sensitivities to changes in temperature, precipitation, carbon dioxide (CO2), and ozone from each approach for the subset of crops, locations, and climate scenarios for which both have been applied. Despite a common perception that statistical models are more pessimistic, we find no systematic differences between the predicted sensitivities to warming from process-based and statistical models up to +2 °C, with limited evidence at higher levels of warming. For precipitation, there are many reasons why estimates could be expected to differ, but few estimates exist to develop robust comparisons, and precipitation changes are rarely the dominant factor for predicting impacts given the prominent role of temperature, CO2, and ozone changes. A common difference between process-based and statistical studies is that the former tend to include the effects of CO2 increases that accompany warming, whereas statistical models typically do not. Major needs moving forward include incorporating CO2 effects into statistical studies, improving both approaches' treatment of ozone, and increasing the use of both methods within the same study. At the same time, those who fund or use crop model projections should understand that in the short-term, both approaches when done well are likely to provide similar estimates of warming impacts, with statistical models generally requiring fewer resources to produce robust estimates, especially when applied to crops beyond the major grains.

Unmanned aerial vehicle (UAV) based remote sensing is gaining momentum worldwide in a variety of agricultural and environmental monitoring and modelling applications. At the same time, the increasing availability of yield monitoring devices in harvesters enables input-target mapping of in-season RGB and crop yield data in a resolution otherwise unattainable by openly availabe satellite sensor systems. Using time series UAV RGB and weather data collected from nine crop fields in Pori, Finland, we evaluated the feasibility of spatio-temporal deep learning architectures in crop yield time series modelling and prediction with RGB time series data. Using Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM) networks as spatial and temporal base architectures, we developed and trained CNN-LSTM, convolutional LSTM and 3D-CNN architectures with full 15 week image frame sequences from the whole growing season of 2018. The best performing architecture, the 3D-CNN, was then evaluated with several shorter frame sequence configurations from the beginning of the season. With 3D-CNN, we were able to achieve 218.9 kg/ha mean absolute error (MAE) and 5.51% mean absolute percentage error (MAPE) performance with full length sequences. The best shorter length sequence performance with the same model was 292.8 kg/ha MAE and 7.17% MAPE with four weekly frames from the beginning of the season.

Water is a major factor limiting crop production in many regions around the world. Irrigation can greatly enhance crop yields, but the local availability and timing of freshwater resources constrains the ability of humanity to increase food production. Innovations in irrigation infrastructure have allowed humanity to utilize previously inaccessible water resources, enhancing water withdrawals for agriculture while increasing pressure on environmental flows and other human uses. While substantial additional water will be required to support future food production, it is not clear whether and where freshwater availability is sufficient to sustainably close the yield gap in cultivated lands. The extent to which irrigation can be expanded within presently rainfed cropland without depleting environmental flows remains poorly understood. Here we perform a spatially explicit biophysical assessment of global consumptive water use for crop production under current and maximum attainable yield scenarios assuming current cropping practices. We then compare these present and anticipated water consumptions to local water availability to examine potential changes in water scarcity. We find that global water consumption for irrigation could sustainably increase by 48% (408 km3 H2O yr−1)-expanding irrigation to 26% of currently rainfed cultivated lands (2.67 × 106 km2) and producing 37% (3.38 × 1015 kcal yr−1) more calories, enough to feed an additional 2.8 billion people. If current unsustainable blue water consumption (336 km3 yr−1) and production (1.19 × 1015 kcal yr−1) practices were eliminated, a sustainable irrigation expansion and intensification would still enable a 24% increase in calorie (2.19 × 1015 kcal yr−1) production. Collectively, these results show that the sustainable expansion and intensification of irrigation in selected croplands could contribute substantially to achieving food security and environmental goals in tandem in the coming decades.