Crop Yield Prediction Research Articles

Applications of remote sensing technology in agriculture: A review of contributions to food security challenges and strategies in developing countries

In the agricultural sphere, particularly in developing countries where food security is still a major concern, remote sensing technology has also surfaced as an important tool. In this review, the usages of remote sensing in agricultural areas and its contributions to food security are surveyed; The overall framework is illustrated dynamically by indicating available image platforms that were instrumental for agriculture application paradigms. This research identifies certain areas where some selected case studies and existing literature are reviewed to serve as proof that remote sensing technology has been tremendously impactful. Areas like crop monitoring, yield prediction, or natural resource management have been very well reported by the literature review process adopted. This field analysis of related studies used highly sophisticated RS sensor data. The challenges like data availability, technological limitations, and socio-economic factors have been discussed besides the strategies, for instance, capacity building, policy interventions, and prospects for technological advancements. These results underscore the vitality and adoption of remote sensing technologies in agricultural practices and policies which is the key driver of improved food security in developing countries.

Integrating Machine Learning for Enhanced Agricultural Productivity: A Focus on Bananas and Arecanut in the Context of India’s Economic Growth

AbstractAgriculture is one of the sectors that has an important impact, taking into account the problem of sufficient food supply on a global level. The process of predicting the yield of crops is among the most challenging undertakings in the agricultural industry. Agriculture is the main source of income for most developing nations. The purpose of the study is to investigate the significant role that agriculture plays in boosting India's economic growth. Additionally, the research considers the challenges posed by a growing population and a changing environment in terms of agricultural production and food security. The research focuses on analysing the complex characteristics of the agricultural industry, with a particular emphasis on the nutritional importance of tropical fruits, notably bananas and arecanut. These fruits are well-known for their vital nutrients and their role in ensuring world food security. This study acknowledges the importance of sustainable agriculture practices and incorporates sophisticated machine learning algorithms as dynamic tools to forecast crop yields and enhance decision-making processes throughout the crop development cycle. The main aim of this study is to create strong machine learning models and statistical techniques that can accurately predict crop yield by combining a variety of environmental parameters, then assess which models outperform each other. Assist yield projections may provide governments and policymakers with valuable information to make well-informed choices about food security, import–export policies, and resource allocation. It facilitates national- and regional-level food supply planning. The validation method utilises important metrics like R square (R2), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). This present research adds to the continuing discussion on using creative methods to promote sustainable agricultural growth and ensure food security.

Investigation of in-field heterogeneities in the development of soybean according to remote sensing data and properties of the plow horizon (on the example of the south of the Far East)

Assessment of crop heterogeneities is one of the key conditions for predicting crop yield and increasing the economic efficiency of farming. The aim of the study is to develop methods for assessing in-field heterogeneities of soybean based on remote sensing data and to determine the relationship between soybean productivity indicators and soil characteristics. The work was carried out on meadow-brown heavy loamy soil, 10 plots of soybean field with a total area of 36.9 ha (Khabarovsk Krai) were selected for sampling in May and August 2023. The research was based on the results of remote sensing data processing (Sentinel-2 satellite, DJI Mavic3M quadrocopter), assessment of soybean productivity indicators, agrochemical, physical and chemical characteristics of soils and micro- and macroelement composition. The spatial distribution of NDVI modeled from Sentinel-2 data (early August) corresponded to the distribution of NDVI from DJI Mavic3M data. NDVI index values in August 2023 were found to be significantly correlated with soybean height (R = 0.64) and number of beans (R = 0.64). Soil moisture has a positive correlation with NDVI (R = 0.87) and soybean height (R = 0.68) for the entire growing season of the crop. NDVI was positively correlated with Hg (R = 0.79) and negatively correlated with pH (R = –0.79). The content of N-NO3 ranged from 2.51 to 6.84 mg/kg (V = 35.12 %), mobile forms of Р2О5 – from 2.47 to 6.07 mg/100 g (V = 33.13 %), К2О – from 4.98 to 9.37 mg/100 g (V = 20.07 %). The variability of N-NO3 and Р2О5 content decreased to 11.61 % and 21.99 % by August. No significant changes in soil bulk composition were observed between the first and second sampling. Variation of content of rare-earth elements (Sc, Y, lanthanides) in the selected sites did not exceed 5 %. By the date of the second sampling a significant decrease by 4–10.5 % (p 0.05) in the content of rare earth elements in soil was noted.

On the issue of forecasting crop yields for the purposes of adaptive landscape agriculture

Long-term monitoring (1998–2023) of the yield of clover-timothy grass stands of the first year of use was carried out in order to find patterns of influence of landscape environmental conditions on it in various agroclimatic conditions. The research was conducted within the moraine hill located at the Gubino VNIIMZ agro-testing site in the Tver region. Soil-forming rocks are two-membered deposits consisting of an upper layer composed of relatively light rocks, underlain by moraine bouldery loam. The grass stands were exploited without fertilizers in a single-cut mode on a field divided into 120 plots. Using regression analysis, the influence of landscape and soil environment factors was determined: relief, physical and agrochemical properties of soils on grass yield, as well as the dependence of the degree of this impact on climatic conditions. It was found that the yield of perennial grasses is most strongly influenced by various fractions of the granulometric composition of soils – from stones to dust (up to 16 % of its variability) and the altitude of the location (up to 38 %), since the thermal and water-air characteristics of soils and vegetation largely depend on them. Terrain characteristics such as steepness and curvature of the surface have a minor impact on grass yield (up to 12 %). The degree of influence of agro-landscape environmental factors on the growth of grasses is largely regulated by fluctuations in weather conditions. “Climate scenarios” of a specific factor – sets of weather parameters under which its effect on the production process of a crop is manifested – in the years of sowing and mowing, as a rule, do not differ fundamentally. Knowing the nature of the influence of climatic factors allows us to more accurately predict crop yields within an agricultural landscape and, thus, optimize the location of crops on the territory of a particular farm.

The impact of weather patterns on inter-annual crop yield variability

Inter-annual variations in crop production have significant implications for global food security, economic stability, and environmental sustainability. Existing crop yield prediction models primarily using meteorological variables may not adequately encapsulate the full breadth of weather influences on crop development processes, such as compound or extreme events. Incorporating weather patterns into crop models could provide a more comprehensive understanding of the environmental conditions affecting growth, enabling more accurate and earlier yield predictions.Our study examines 30 distinct UK Met Office weather patterns (MO30) based on mean sea level pressure. We investigate their association with weather conditions that limit winter wheat yield in the UK (1990–2020). Blocked, negative North Atlantic Oscillation (NAO) patterns create the highest risk of temperatures that are below optimal for crop yield. However, the connection between weather patterns and yield is complex, with differing effects at a regional scale and even at which point in the growth cycle they appear. It was found that anticyclonic weather patterns during sowing, emergence, vernalisation, anthesis, and grain filling exhibit a relationship with good crop yields with a Spearman correlation coefficient of up to 0.55 for a single weather pattern (WP3 during vernalisation in South East England), whilst cyclonic patterns can help during the terminal spikelet phenological phase. The strongest positive correlations were during sowing, emergence, and vernalisation, whilst the largest negatives were observed in anthesis and grain filling.The potential of combining weather patterns with existing crop simulation models to produce earlier and more accurate yield predictions is shown. This would enable effective crop management and climate mitigation strategies, critical to strengthening food security. Projected changes in weather pattern occurrences in the late 21st century will likely reduce crop yields. This is due to increased cyclonic weather patterns, which bring warmer, wetter conditions during the wheat's vernalisation stage, followed by warmer, drier conditions during the anthesis and grain-filling phases.

An Improved Reptile Search Algorithm with Multiscale Adaptive Deep Learning Technique and Atrous Spatial Pyramid Pooling for IoT-based Smart Agriculture Management

Smart farming is an enhanced option for increasing food production, resource management and labour. Existing prediction methods need trained experts to analyse the data, which is a time-consuming process, and thus, there is a need for smart farming with the Internet of Things (IoT). Hence, a well-developed IoT-assisted smart agriculture model is proposed for managing agricultural needs to improve the economic value of farmers. The proposed framework constitutes four major aspects like Crop prediction, Crop yield prediction, Plant disease prediction and Smart irrigation. Initially, the crop images are taken as the input and fed to the Multi-scale Adaptive and Attention-based Convolution Neural Network with Atrous Spatial Pyramid Pooling (MACNN-ASPP), where the dissimilar crops are classified and obtained. In the second aspect, the crop image as well as crop-related data, are fetched from the data sources and given as input. Further, the deep features of the image are extracted that are added with soil and environment condition data. Then this feature is subjected to the Multi-scale Adaptive and Attention-based One-Dimensional Convolution Neural Network with Atrous Spatial Pyramid Pooling (MA1DCNN-ASPP) for crop yield prediction. While in the third aspect, the leaf images are assembled from the data file and fed as input to the MACNN-ASPP for detecting the variety of diseases affecting the plants. In the final aspect, smart irrigation is done by collecting field images with related data. Further, the deep features retrieved from the field images are applied to MA1DCNN-ASPP, where the different conditions of the field will be attained. In order to develop the model adaptively, the hyper-parameters in the network are optimised using the Improved Reptile Search Algorithm (IRSA). Finally, the investigation is done over the proposed methodology using multiple evaluation metrics. In contrast with other approaches, the proposed smart agriculture outperforms the performance of managing crops without any hazardous effects. Accuracy validation executed in the implemented IRSA-MACNN-ASSP-based crop yield prediction model accomplished better efficiency as 6.89%, 4.45%, 2.19% and 1.08% better than the classical techniques like CNN, LSTM, 1DCNN and MA1DCNN-ASPP.

Integrating solar-induced chlorophyll fluorescence with traditional remote sensing and environmental variables for enhanced rice yield prediction in Nepal using machine learning

Rice is a vital cereal crop providing essential food for Nepal. To mitigate climate risks and ensure food security, especially with climate change and increasing extreme weather events, it is imperative and a prerequisite to have timely and reliable rice yield prediction. While traditional vegetation indices (VIs) and environmental variables are commonly used in rice yield prediction, the potential of solar-induced chlorophyll fluorescence (SIF), despite its greater sensitivity, has been explored in limited studies. Furthermore, integrating SIF with other remote sensing and environmental data for regional crop yield modeling still needs to be explored. This study aims to address these gaps by incorporating SIF to enhance rice yield prediction in Nepal, offering a novel approach to improving model accuracy. This study uses multi-source data and machine learning algorithms to study 22 major rice-growing districts in the Terai region of Nepal. Random forest (RF), support vector machine (SVR), gradient boosting regressor (GBR), and least absolute shrinkage and selection operator (LASSO) algorithms were employed to predict crop yield using various combinations of input features. Machine learning models were trained and tested over four different time windows within the growing period of rice, using 15 years of rice yield data from 2003 to 2017. Our analysis reveals that GBR out-performed other machine learning algorithms when using input features from July to September, achieving root mean square error (RMSE) and the ratio of RMSE (RRMSE) to observed mean values of 250 kg/ha and 8.6%, respectively. The findings also reveal that incorporating SIF alongside traditional remote sensing and environmental variables significantly enhances the model's prediction accuracy. These findings are valuable for ensuring food security, optimizing agricultural resource management, and supporting decision-making for farmers, policymakers, and supply chain stakeholders.

Modelling and Performance Evaluation of Machine Learning Techniques in Forecasting Cereal Yield for Shri Ganganagar Region, Rajasthan, India

One of agriculture's most difficult issues is predicting crop yield. Crop yield forecasting enables necessary decisions to be made to guarantee food security. The current study looks into the use of statistical and machine learning approaches for wheat and rice yield prediction using long-term weather and yield data of ShriGanganagar, Rajasthan, India. Weather-based models may give accurate crop production estimates, but choosing the right model for agricultural output projections can be difficult. As a result, different models were compared in this study to determine the best model for rice and wheat yield prediction including Multiple linear regression (SMLR), Artificial neural network (ANN), Least absolute shrinkage and selection operator (LASSO), Elastic net (ELNET), Ridge regression, and K-nearest neighbor (K-NN). K-NN outperformed ANN in rice crops and fared better in wheat crops based on the lowest nRMSE value. Ridge regression based on nRMSE was the next best model for Rice yield prediction in the examined region, and KNN was the second best model for Wheat crop.

Rock Melon Crop Yield Prediction using Supervised Classification Machine Learning on Cloud Computing

Precision agriculture is a technology-driven approach to farmer to improve their crop yields and reduce costs. One of the major challenges facing farmers today is the lack of precise prediction which leads to decreased production and mismanagement of labour and resource. Precision technology is costly, and they only rely on manual observations which are less precise. Crop yield prediction systems on cloud computing can solve both problems by predicting the harvested fruit at earlier stages of farming and ease farmers to make decisions. In this study, we proposed a crop yield prediction system for farmers that utilizes cloud computing and machine learning techniques. The system uses data on the physical growth of the plant such as plant’s height at 15 and 30 days after transplant, type of pollination treatment, condition of the leaves, and their variety to predict the crop yield at the early stage. Logistic regression, k-nearest neighbour, and random forest classifier were used to compare the accuracy of the model. Our result shows that by using a random forest classifier, it can achieve an accuracy of 91% which is higher than logistic regression which is only 73% of accuracy, and k-nearest neighbour with 82% accuracy. The study highlights the potential of precision agriculture, cloud computing, and machine learning to revolutionize the way farmers manage their crops and increase their efficiency and productivity, even with the limited resources and hardware that many farmers have.

Progress in Research on Deep Learning-Based Crop Yield Prediction

In recent years, crop yield prediction has become a research hotspot in the field of agricultural science, playing a decisive role in the economic development of every country. Therefore, accurate and timely prediction of crop yields is of great significance for the national formulation of relevant economic policies and provides a reasonable basis for agricultural decision-making. The results obtained through prediction can selectively observe the impact of factors such as crop growth cycles, soil changes, and rainfall distribution on crop yields, which is crucial for predicting crop yields. Although traditional machine learning methods can obtain an estimated crop yield value and to some extent reflect the current growth status of crops, their prediction accuracy is relatively low, with significant deviations from actual yields, and they fail to achieve satisfactory results. To address these issues, after in-depth research on the development and current status of crop yield prediction, and a comparative analysis of the advantages and problems of domestic and foreign yield prediction algorithms, this paper summarizes the methods of crop yield prediction based on deep learning. This includes analyzing and summarizing existing major prediction models, analyzing prediction methods for different crops, and finally providing relevant views and suggestions on the future development direction of applying deep learning to crop yield prediction research.

Winter Wheat Yield Prediction Based on the ASTGNN Model Coupled with Multi-Source Data

Timely and accurate prediction of winter wheat yields, which is crucial for optimizing production management, maintaining supply–demand balance, and ensuring food security, depends on interactions among numerous factors, such as climate, surface characteristics, and soil quality. Despite the extensive application of deep learning models in this field, few studies have analyzed the effect of the large-scale geospatial characteristics of neighboring regions on crop yields. Therefore, we present an attention-based spatio-temporal Graph Neural Network (ASTGNN) model coupled with geospatial characteristics and multi-source data for improved accuracy of winter wheat yield estimation. The datasets used in this study included multiple types of remote sensing, meteorological, soil, crop yield, and planting area data for Anhui, China, from 2005 to 2020. The results showed that multi-source data led to higher prediction performance than single-source data, and enabled accurate prediction of winter wheat yields three months prior to harvest. Furthermore, the ASTGNN model provided better prediction performance than two traditional crop yield prediction models (R2 = 0.70, RMSE = 0.21 t/ha, MAE = 0.17 t/ha). Therefore, ASTGNN enhances the accuracy of crop yield prediction by incorporating geospatial characteristics. This research has implications for improving agricultural production management, promoting the development of digital agriculture, and addressing climate change in agriculture.

Crop yield prediction with environmental and chemical variables using optimized ensemble predictive model in machine learning

Abstract Enhanced crop yield prediction is necessary for agronomists to make dynamic premonsoon decisions. The input variables precipitation, temperature, evaporation, wind speed, and chemical use influence crop yield estimations. In this study, we analyzed the correlation between crop yield and input features, and scaled up the prediction power of the crop yield model using optimized ensemble learning for machine learning. The proposed model is expected to deal with the limitations of existing models by minimizing effort and data requirements. It achieved better performance than the other approaches with a MSE (Mean Squared Error) of 42963, MAE (Mean Absolute Error) of 87, and R 2 (Coefficient of Determination) of 0.96. The findings of this study have important suggestions for agricultural management and policy-making. The proposed model offers possible applications for enhancing crop yield prediction across various perspectives, thereby assisting more informed decision-making in agriculture.

MResGat: Multi-head Residual Dilated Convolution Assisted Gated Unit Framework for Crop Yield Prediction

The importance of predicting crop yields has increased due to growing concerns of surrounding food security. Early forecasting of crop yields holds a pivotal role in avoiding starvations by estimating the food supply available for the expanding global population. Several Deep Learning (DL) and Machine Learning (ML) techniques are involved to develop effective and accurate crop yield prediction model. Nevertheless, existing models faces some limitations such as less accuracy, high error rate because of noisy data, high training time and extracted less effective features for prediction. To overcome these issues, the novel DL methodology is introduced for attaining high accurate crop yield prediction. Initially, the soil, weather and other resources big data are collected from the various agriculture field. In data collection phase, the input data of larger size are stored in the Hadoop platform for the purpose of storing as well as processing the entire data in a distributed manner. The data are pre-processed through the utilization of Missing value imputation and z-score based data normalization. From the pre-processed data, the optimal features are considered using Integrated Correlation Random recursive elimination (InCorRe) approach. Based on the previous soil and weather information, the suitable yield of crops can be predicted using Multi head Residual dilated convolution assisted gated unit (MResGat) model. Finally, the losses of the network model can be optimized using African vulture optimization algorithm (AVO). The proposed method is evaluated using the several performance metrics, which achieved 0.023% of MSE value and 0.036% of MAE values.

Leveraging crop yield forecasts using satellite information for early warning in Senegal

Agricultural losses driven by climate variability and anthropogenic pressures have severely impacted food security in Senegal. There is a crucial need to generate early warning signals for the upcoming season to enhance food security in response to the sudden climate shocks like drought. In this study, we investigated the spatial distribution of maize and groundnut using factor analysis with a principal component approach. We aimed to identify suitable predictors of crop yields for the development of a seasonal yield prediction model. Subsequently, multi-regression analysis was performed to predict crop yield based on various combinations of satellite-derived vegetation and climate (rainfall) datasets as well as agronomic data from Senegal's 40 districts between 2010 and 2021. Studies revealed a strong correlation between seasonal rainfall (May to September) and crop yield: a 10–20% decline in rainfall can lead to crop losses. The accuracy of the yield prediction model, built on the best performing scenarios for each district based on monsoon onset, duration, and planting time, exceeded 0.5 (R-squared) for all districts when combining rainfall and normalized difference vegetation index (NDVI) data. The model prediction accuracy varied between 0.6 and 0.8 for major crop growing areas. The study emphasizes that refining the yield prediction model using machine learning techniques can improve its accuracy and enable its implementation in early warning systems. This enhanced capability could bolster Senegal's resilience to climate change by aiding decision-makers and planners in developing more effective strategies to ensure food security.

Predictive Cultivation: Integrating Meteorological Data and Machine Learning for Enhanced Crop Yield Forecast

Agriculture is a key component of Telangana’s economy, and greater performance in this sector is crucial for inclusive growth. A central challenge is yielding estimation to predict crop yields before harvesting. This paper addresses this challenge with machine learning approaches includes Naive Bayes, KNN and Random Forest. The parameters considered for model testing are crop, season, rainfall and location. This paper includes a case study of Telangana with the help of Telangana weather data set to provide analysis on the key factors like overall rainfall recorded with respect to each Mandal, overall seasonal yield in selected years, seasonal yield of major crops like Bengal gram, groundnut and maize, and overall yield in two different agricultural seasons: rabi and kharif. Random forest machine learning model produces highest accuracy of 99.32% when compared with other process models.

Innovations in Agricultural Forecasting: A Multivariate Regression Study on Global Crop Yield Prediction

Innovations in Agricultural Forecasting: A Multivariate Regression Study on Global Crop Yield Prediction

A Deep–Learning Network for Wheat Yield Prediction Combining Weather Forecasts and Remote Sensing Data

Accurately predicting winter wheat yield before harvest could greatly benefit decision-makers when making management decisions. In this study, we utilized weather forecast (WF) data combined with Sentinel-2 data to establish the deep-learning network and achieved an in-season county-scale wheat yield prediction in China’s main wheat-producing areas. We tested a combination of short-term WF data from the China Meteorological Administration to predict in-season yield at different forecast lengths. The results showed that explicitly incorporating WF data can improve the accuracy in crop yield predictions [Root Mean Square Error (RMSE) = 0.517 t/ha] compared to using only remote sensing data (RMSE = 0.624 t/ha). After comparing a series of WF data with different time series lengths, we found that adding 25 days of WF data can achieve the highest yield prediction accuracy. Specifically, the highest accuracy (RMSE = 0.496 t/ha) is achieved when predictions are made on Day of The Year (DOY) 215 (40 days before harvest). Our study established a deep-learning model which can be used for early yield prediction at the county level, and we have proved that weather forecast data can also be applied in data-driven deep-learning yield prediction tasks.

A Combined Long Short-Term Memory and Temporal Convolutional Network Model for Crop Yield Prediction

A Combined Long Short-Term Memory and Temporal Convolutional Network Model for Crop Yield Prediction

Multi-scale hybrid modeling of plant growth in response to environmental conditions and soil nutrients availability

Crop modeling plays a crucial role in agriculture, aiding our understanding and prediction of crop growth and yield in diverse environmental conditions. This study aims to develop a comprehensive mathematical model describing plant growth in response to environmental conditions and soil nutrient availability. To achieve this, we relied on a field experiment with lettuce plants under varying environmental conditions. Employing growth models such as logistic, Gompertz, Aikman & Scaife, and Scaife, Cox & Morris, we assessed the influence of time, day-degrees, and effective-day-degrees across different plant densities and during distinct periods throughout the year. In general, describing plant growth in terms of day-degrees or effective-day-degrees yielded an improved model fit and more precise estimations of growth parameters. As a result, we described the growth of plant length in terms of effective-day-degrees instead of time in the equations of the Bessonov-Volpert system. Additionally, we modified the equation describing plant length growth using previously fitted functions. By incorporating these adjustments, we characterized the one-dimensional growth of plant weight under varying environmental conditions without branching, using the Bessonov-Volpert model. This study contributes valuable insights into crop modeling techniques, refining our understanding of optimizing plant growth under different environmental conditions.

Applying double cropping and interactive irrigation in the North China Plain using WRF4.5

Abstract. Irrigated cultivation exerts a significant influence on the local climate and the hydrological cycle. The North China Plain (NCP) is known for its intricate agricultural system, marked by expansive cropland, high productivity, compact rotation, a semi-arid climate, and intensive irrigation practices. As a result, there has been considerable attention on the potential impact of this intensive irrigated agriculture on the local climate. However, studying the irrigation impact in this region has been challenging due to the lack of an accurate simulation of crop phenology and irrigation practices within the climate model. By incorporating double cropping with interactive irrigation, our study extends the capabilities of the Weather Research Forecast (WRF) model, which has previously demonstrated commendable performance in simulating single-cropping scenarios. This allows for two-way feedback between irrigated crops and climate, further enabling the inclusion of irrigation feedback from both ground and vegetation perspectives. The improved crop modeling system shows significant enhancement in capturing vegetation and irrigation patterns, which is evidenced by its ability to identify crop stages, estimate field biomass, predict crop yield, and project monthly leaf area index. The improved simulation of large-scale irrigated crops in the NCP can further enhance our understanding of the intricate relationship between agricultural development and climate change.