Applications of Machine Learning in Agrometeorological Forecasting and Modeling: A Short Review from the Journal of Agrometeorology

optimal resource allocation and full or partial automation of farm processes (Smith, 2018; Dengel, 2013). Precision agriculture aims to maximize crop yields and farm profits while reducing environmental costs (Chlingaryan et al., 2018; Schieffer & Dillon, 2015) by ensuring optimal use of water, fertilizers, and phytosanitary products (Ruiz-Real et al., 2020). Smart farming goes one step further and incorporates informed decision making based on data and context-awareness (Sundmaeker et al., 2016) . Smart farming is expected to bridge the gap between farming and AI (Chung et al., 2015) . With the help of AI, food of higher nutritional value could be produced more efficiently in more stable supplies and with less environmental costs (Osinga et al., 2022). Therefore, AI and machine learning will play a key role in the twin goals of feeding a growing population while making food systems sustainable (Walter et al., 2017) and climate neutral. Both precision farming and smart farming seek to improve crop yields, and accurate yield forecasts are crucial to achieve that. Horie et al. (1992) list three advantages of early season crop yield forecasts. First, yield forecasts are indispensable for food security planning. Second, farmers can adapt farm management practices, such as irrigation and fertilization, based on estimates of the final yield. Third, reliable yield forecasts enable farmers to make better marketing plans for their products. For these advantages to be realized, all stakeholders need access to consistent and unbiased yield forecasting models. Expected yields strongly influence the price of produce, and public availability of forecasting models will reduce information asymmetry among players in the commodity markets (Jiang et al., 2020) . Machine learning and other AI technologies can help democratize access to data and yield forecasting models useful for farm management, market pricing, logistics and food security planning. Mitchell (1997) provides a concise definition of machine learning: "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E." The experience can be a set of training data points, the task can be crop yield prediction and the performance measure can be accuracy, root mean square error (RMSE), etc. Machine learning makes predictions using predictors or features. Features are aggregations or summaries of input data for specific spatial and temporal windows. Feature design or feature engineering is the process of using prior (domain) knowledge to create features that influence or explain the variability in the labels or prediction targets, such as crop yield. Supervised machine learning (Figure 1 .2) uses a training set of examples which includes features or predictors as well as the output label (e.g. crop yield) to learn a function which relates feature values to the labels. When each data point has a corresponding label, the model gets strong supervision from the label. When label data is not available for all data points at high resolution, learning is still possible using high resolution features and low resolution labels. High resolution forecasts can be aggregated to low resolution and compared with the labels. Such learning is an example of weakly supervised learning (Zhou, 2018). Reliable crop yield forecasts for a growing season are valuable to many stakeholders, such as farmers, commodity traders, logistics companies, policymakers and food aid programs (Basso & Liu, 2019; Schauberger et al., 2020). Forecasts can impact farm management practices, market information and food security measures. Farmers adjust farm management practices based on yield outlooks. Businesses and governments respond to conditions in commodity markets (USDA-NASS, 2012). Similarly, crop monitoring and yield forecasting contribute to the implementation of the European Union's Common Agricultural Policy (van der Velde et al., 2019). Furthermore, certain organizations, such as the International Grains Council Remote sensing provides indirect indicators of crop yield by measuring observed radiance In this thesis, large-scale crop yield forecasting means scaling yield forecasting to large and diverse areas in two dimensions (Figure 1 .3): from one country and crop to multiple countries and crops at continental scale, and from country-level forecasts to sub-national and grid-level forecasts. Large-scale yield forecasting systems around the world use some combination of methods described in Section 1.3.2, but not machine learning. Here we briefly describe three systems from Europe and North America. Other large-scale systems, such as the China CropWatch (Wu et al., 2014) and the Mahalanobis National Crop Forecast Centre of India (Mahalanobis Centre, 2022), share some similarities with those described. The European Commission's Joint Research Centre Directorate for Sustainable Resources, 1.4 Large-scale crop yield forecasting 9 1.4.3 Machine learning for large-scale crop yield forecasting Operational large-scale yield forecasting systems commonly build linear statistical models using outputs of crop models, remote sensing and surveys. Similarly, Lobell et al. (2015) combined crop model simulations, remote sensing data and linear regression to build a scalable crop yield mapping tool for corn and soybean in the US. While linear models are simple and interpretable, they do not always capture complex relationships between predictors and yield. Combining the strengths of crop models, remote sensing and machine learning is a promising solution to forecast crop yields at large scale. Crop models provide agronomic information, remote sensing provides crop state with increasing detail and machine learning 1. A baseline for large scale: Design a generic explainable, modular and reusable 1.5 Research objectives Figure 1.4 shows how the sub-objectives are related to each other. Sub-objective 1 focuses on a generic, modular and reusable workflow that is based on agronomic principles and produces results that serve as the baseline for further improvements. Sub-objective 2 improves the workflow and tests its scalability to many crops and locations in Europe. Sub-objectives 1 and 2 both rely on experts for feature design. Sub-objective 3 uses deep learning to automate feature extraction and evaluates the interpretability of features learned. Sub-objective 4 addresses data requirements at high resolution by producing high resolution forecasts in the absence of high resolution yield data.

The article provides an overview of the accuracy of various yield forecasting algorithms and offers a detailed explanation of the models and machine learning algorithms that are required for crop yield forecasting. A unified crop yield forecasting methodology is developed, which can be adjusted by adding new indicators and extensions. The proposed methodology is based on remote sensing data taken from free sources. Experiments were carried out on crops of cereals, legumes, oilseeds and forage crops in eastern Kazakhstan. Data on agricultural lands of the experimental farms were obtained using processed images from Sentinel-2 and Landsat-8 satellites (EO Browser) for the period of 2017–2022. In total, a dataset of 1600 indicators was collected with NDVI and MSAVI indices recorded at a frequency of once a week. Based on the results of this work, it is found that yields can be predicted from NDVI vegetation index data and meteorological data on average temperature, surface soil moisture and wind speed. A machine learning programming language can calculate the relationship between these indicators and build a neural network that predicts yield. The neural network produces predictions based on the constructed data weights, which are corrected using activation function algorithms. As a result of the research, the functions with the highest prediction accuracy during vegetative development for all crops presented in this paper are multi-layer perceptron, with a prediction accuracy of 66% to 99% (85% on average), and polynomial regression, with a prediction accuracy of 63% to 98% (82% on average). Thus, it is shown that the use of machine learning and neural networks for crop yield prediction has advantages over other mathematical modelling techniques. The use of machine learning (neural network) technologies makes it possible to predict crop yields on the basis of relevant data. The individual approach of machine learning to each crop allows for the determination of the optimal learning algorithms to obtain accurate predictions.

Indian agriculture, a cornerstone of the national economy and the primary source of livelihood for a majority of its population, faces unprecedented challenges due to increasing climate variability and the structural constraints of smallholder farming. Agro-Climatic Decision Support Systems (DSS) offer a promising pathway to enhance resilience and productivity by providing timely, data-driven insights. This paper investigates the application of diverse Machine Learning (ML) models as the core intelligence engine for such DSS tailored to the Indian context. The objective is to comprehensively review current ML applications in Indian agriculture, propose a conceptual ML-DSS pipeline leveraging heterogeneous national data sources (including meteorological, soil health, remote sensing, and agricultural statistics), critically analyze the pertinent challenges impeding widespread adoption, and identify key future research directions. The analysis reveals that while ML techniques, ranging from traditional algorithms like Random Forest and Support Vector Machines to advanced deep learning architectures like Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Transformers, demonstrate significant potential for optimizing critical farming decisions—such as crop selection, yield forecasting, pest and disease management, and resource optimization—substantial hurdles remain. These challenges primarily revolve around India's complex data ecosystem, characterized by fragmentation, lack of standardization, variable quality, and difficulties in multimodal data integration. Furthermore, issues of model localization for diverse agro-climatic zones, scalability, and ensuring digital inclusion for smallholder farmers present significant barriers. Overcoming these requires a multi-pronged approach involving technological innovation (e.g., Federated Learning, Edge ML, Natural Language Processing), robust data governance frameworks, and targeted capacity building. Ultimately, well-designed ML-driven DSS are vital tools for navigating climate uncertainty, bolstering food security, enhancing the sustainability of agricultural practices, and improving the economic well-being of India's farmers.

Machine learning (ML) techniques discover knowledge from large amounts of data. Modeling in ML is becoming essential to software systems in practice. The accuracy and efficiency of ML models have been focused on ML research communities, while there is less attention on validating the qualities of ML models. Validating ML applications is a challenging and time-consuming process for developers since prediction accuracy heavily relies on generated models. ML applications are written by relatively more data-driven programming based on the black box of ML frameworks. All of the datasets and the ML application need to be individually investigated. Thus, the ML validation tasks take a lot of time and effort. To address this limitation, we present a novel quality validation technique that increases the reliability for ML models and applications, called MLVal. Our approach helps developers inspect the training data and the generated features for the ML model. A data validation technique is important and beneficial to software quality since the quality of the input data affects speed and accuracy for training and inference. Inspired by software debugging/validation for reproducing the potential reported bugs, MLVal takes as input an ML application and its training datasets to build the ML models, helping ML application developers easily reproduce and understand anomalies in the ML application. We have implemented an Eclipse plugin for MLVal that allows developers to validate the prediction behavior of their ML applications, the ML model, and the training data on the Eclipse IDE. In our evaluation, we used 23,500 documents in the bioengineering research domain. We assessed the ability of the MLVal validation technique to effectively help ML application developers: (1) investigate the connection between the produced features and the labels in the training model, and (2) detect errors early to secure the quality of models from better data. Our approach reduces the cost of engineering efforts to validate problems, improving data-centric workflows of the ML application development.

Forecasting crop yields is important for food security, in particular to predict where crop production is likely to drop. Climate records and remotely-sensed data have become instrumental sources of data for crop yield forecasting systems. Similarly, machine learning methods are increasingly used to process big Earth observation data. However, access to data necessary to train such algorithms is often limited in food-insecure countries. Here, we evaluate the performance of machine learning algorithms and small data to forecast yield on a monthly basis between the start and the end of the growing season. To do so, we developed a robust and automated machine-learning pipeline which selects the best features and model for prediction. Taking Algeria as case study, we predicted national yields for barley, soft wheat and durum wheat with an accuracy of 0.16–0.2 t/ha (13-14% of mean yield) within the season. The best machine-learning models always outperformed simple benchmark models. This was confirmed in low-yielding years, which is particularly relevant for early warning. Nonetheless, the differences in accuracy between machine learning and benchmark models were not always of practical significance. Besides, the benchmark models outperformed up to 60% of the machine learning models that were tested, which stresses the importance of proper model calibration and selection. For crop yield forecasting, like for many application domains, machine learning has delivered significant improvement in predictive power. Nonetheless, superiority over simple benchmarks is fully achieved after extensive calibration, especially when dealing with small data.

SASYA: An integrated framework for crop biophysical parameter retrieval and within-season crop yield prediction with SAR remote sensing data

Machine learning (ML) applications face many new, hardly predictable aspects in their production environments. Detecting new aspects in an ML production environment and understanding their impacts on the ML application is crucial if organizations are to ensure ML applications functionality. A monitoring entity is essential if one is to monitor ML applications in their production environments, to both continually minimize risks and improve ML application’s performance. But existing monitoring approaches are struggling to deal with specifics that arise from ML applications. We aim at deriving monitoring practices and providing a holistic view over required steps in successful ML applications monitoring. Since there has been little research on this topic, we followed a qualitative research approach, i.e., we conducted an interview study combined with a multivocal literature review. Thus, we provide a theoretical framework of an ML-enabled agent in its production environment, five characteristics of ML applications’ production environments and 17 monitoring practices – 14 practices arranged sequentially on a typical quality management cycle and three cross-sectional practices. To outline the ML specifics that arise in monitoring ML applications, we investigate the five ML production environment characteristics’ influences on the ML monitoring practices.

Accurate and timely crop yield forecasts are critical to realizing global food security, balancing international grain trade, and promoting sustainable agricultural development. By providing consistent and large-scale observations, remote sensing technology has become indispensable in crop yield estimation across local, regional, and global scales. Over the past four decades, numerous crop yield forecasting approaches have been developed, including regression-based statistical models, machine learning, semi-empirical models, crop model-data assimilation (DA), and advanced deep learning (DL) approaches. This review comprehensively explores the latest advancements in these methodologies, critically evaluating their strengths and limitations in practical applications. In particular, this article highlights the challenges associated with spatiotemporal variability, environmental stress factors, and model scalability, offering potential solutions to enhance the accuracy and reliability of regional and global crop yield predictions. Besides, a selection strategy is also outlined, providing guidance on choosing the most appropriate yield estimation methods tailored to specific application objectives, data availability, and geographic scales. We also identify key factors affecting crop yield forecasting and offer insights into future trends and directions of development. Furthermore, we underscore the greatest potential of integrating artificial intelligence (AI) and remote sensing technologies with process-based crop growth models through DA techniques. This fusion holds significant promise for addressing the pressing need for accurate and scalable yield forecasts. As the global demand for food intensifies and the need for sustainable agriculture grows, the development and application of these advanced methodologies will be instrumental in ensuring resilient food systems and supporting sustainable agricultural practices.

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.

Climate change has emerged as one of the most significant global challenges, directly affecting agricultural productivity and food security. Rising temperatures, irregular rainfall patterns, and fluctuations in humidity are altering crop growth cycles and reducing yield stability. In developing countries such as India, where agriculture depends largely on monsoon rainfall and traditional cultivation practices, predicting crop productivity under variable climatic conditions becomes essential for strategic planning and climate-resilient farming. This research investigates the impact of climate change on crop productivity using Machine Learning (ML) models, leveraging multi-year historical data that includes climatic parameters (temperature, rainfall, humidity, and solar radiation), soil characteristics (nitrogen, phosphorus, potassium, pH), and crop yield records. Multiple ML algorithms—including Linear Regression, Support Vector Machine (SVM), Random Forest (RF), XGBoost, and Artificial Neural Networks (ANN)—were developed and evaluated. To improve predictive capability, a Hybrid Ensemble Model combining Random Forest, XGBoost, and ANN was proposed. Data preprocessing involved handling missing data, feature scaling, correlation filtering, and creating derived indices such as Growing Degree Days (GDD) and Rainfall Anomaly Index (RAI). The models were evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and coefficient of determination (R²). The Ensemble Model outperformed all baseline and advanced models, achieving R² = 0.94, indicating a high correlation between predicted and actual crop yields. Feature importance analysis revealed that rainfall and soil nitrogen are the dominant predictors, followed by temperature and humidity. The study also highlights regional disparities, showing that arid and coastal zones are more vulnerable to climatic variability. The findings confirm that ML models can accurately forecast crop yields and help farmers and policymakers adopt climate-smart agricultural strategies. The developed framework can serve as a decision-support system for resource optimization, early warning, and sustainable agricultural planning. Keywords: Climate Change, Crop Productivity, Machine Learning, Ensemble Model, XGBoost, Random Forest, Predictive Analytics, Sustainable Agriculture, Climate Smart Farming, Crop Yield Forecasting

Seasonal forecasts of crop yield are important components for agricultural policy decisions and farmer planning. A wide range of input data are often needed to forecast crop yield in a region where sophisticated approaches such as machine learning and process-based models are used. This requires considerable effort for data preparation in addition to identifying data sources. Here, we propose a simpler approach called the Analogy Based Crop-yield (ABC) forecast scheme to make timely and accurate prediction of regional crop yield using a minimum set of inputs. In the ABC method, a growing season from a prior long-term period, e.g., 10 years, is first identified as analogous to the current season by the use of a similarity index based on the time series leaf area index (LAI) patterns. Crop yield in the given growing season is then forecasted using the weighted yield average reported in the analogous seasons for the area of interest. The ABC approach was used to predict corn and soybean yields in the Midwestern U.S. at the county level for the period of 2017–2019. The MOD15A2H, which is a satellite data product for LAI, was used to compile inputs. The mean absolute percentage error (MAPE) of crop yield forecasts was <10% for corn and soybean in each growing season when the time series of LAI from the day of year 89 to 209 was used as inputs to the ABC approach. The prediction error for the ABC approach was comparable to results from a deep neural network model that relied on soil and weather data as well as satellite data in a previous study. These results indicate that the ABC approach allowed for crop yield forecast with a lead-time of at least two months before harvest. In particular, the ABC scheme would be useful for regions where crop yield forecasts are limited by availability of reliable environmental data.

Prediction and forecasting of crop yield recently plays a vital role in the field of Agriculture. Drastic changes in climatic conditions, changes in rainfall season, and lack of nutrients content in the soil etc., due to major factors such as rapid industrialisation, global warming and pollution. This leads to the farmers’ predictions based on their own agricultural experiences on various crop yields based on external factors gone wrong. This results in farmers not getting adequate yield and suffering from financial loss. Machine learning and time series models are involved in this research work to carry out prediction and forecast of corn and soybean crop production over time through mobile application and it consist of various regression algorithms of machine learning such as multiple linear regression (MLR), decision tree regression (DTR), random forest tree regression (RFTR), k-nearest neighbour (KNN) and gradient boosting regression (GBR) are used for crop yield prediction. Time series models such as auto regression (AR), moving average (MA), auto regression integrated moving average (ARIMA) and vector auto regression (VAR) used for forecast of crop production. Comparative analysis also made between machine learning and time series models, in which GBR of machine learning outperformed other machine learning models with 92.648% predicted yield accuracy and VAR of time series model outperformed other time series models with 94.367% forecasted yield accuracy. Regression metrics such as mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) are also involved in predicting crop yields.

This chapter explores the transformative potential of Artificial Intelligence (AI) and Machine Learning (ML) applications in fostering data-informed leadership within higher education institutions. With data available in academic settings, leveraging AI and ML technologies becomes imperative for effective decision-making and strategic planning. Through a comprehensive examination of case studies, best practices, and emerging trends, this chapter elucidates how AI and ML enable leaders in higher education to harness actionable insights from diverse data sources, optimize resource allocation, enhance student outcomes, and drive innovation across various operational domains. Furthermore, it addresses key considerations such as ethical implications, privacy concerns, and the importance of human expertise in complementing AI-driven decision support systems. By embracing AI and ML applications, leaders in higher education can navigate complexities, anticipate future challenges, and propel their institutions toward excellence and sustainability in the rapidly evolving educational landscape.

Machine learning (ML) and deep learning can be used in the smartest way possible to improve productivity in agriculture. The Food and Agriculture Organization's research shows that the crop's production is rising. One of the finest methods to monitor agricultural yield is through smart agriculture. Applications of ML and deep learning help to discover and resolve problems that crop growth encounters. In agriculture, the production of crops can be enhanced by applying machine learning and deep learning methodologies. These methods demonstrate the rapid advancement of artificial intelligence in the agriculture sector. The idea of “smart farming” keeps an eye on all processes, disease prediction, and agricultural pests. ML is used to extract meaningful information from huge datasets. Deep learning evaluates structural characteristics, meteorological data, and climatic factors to help anticipate agricultural diseases using practical and economical techniques. The deep-learning techniques enhance agricultural research's capacity to sense the overall classification of agriculture.

Machine learning in medical applications is one of the focus areas of the researchers these days. Machine Learning with the application of Artificial Intelligence is not only giving solutions to the complex problems but also revolutionised the medical field. The main motive of machine learning is to improve its learning process over time by taking all the relevant data and information in the form of different inputs and observations. This study reviews different medical disease prediction and detection techniques with the help of distinct deep learning & machine learning models. The problems related to medical diseases, like cancer related diseases, heart, lung, thyroid and kidney diseases are being discussed in this article. Detection and analysing of medical diseases is one of the prominent applications of machine and deep learning. Deep learning as a technology offers a huge set of different and innovative tools which are relevant to different issues faced in the field of medical image processing. This study will discuss about the applications of Machine Learning, and then discuss some of the advancements done in different diseases like breast cancer, heart disease, skin disease, kidney disease etc.