Revolutionizing Crop Management: Current Applications of AI Technology

Long-Form Article

20 min readMay 20, 2024

AI optimizes precision agriculture by improving planting schedules, irrigation, and harvesting. Machine learning analyzes soil, weather, and historical data to determine ideal planting times, increasing yields and reducing the risk of crop failure. Sensor networks and deep learning models detect disease early to enhance crop management. Robotic harvesting systems, soil moisture sensors, and AI-driven irrigation conserve water and increase plant health. Predictive analytics, satellite imagery, yield prediction models, and IoT devices increase resource use efficiency, nitrogen use efficiency, productivity, and sustainability. All of these topics are discussed in this long-form article.

by Jorge Luis Alonso with ChatGPT-4o

Content Outline

Introduction
Precision Farming
2.1 Optimizing planting schedules, irrigation, and harvesting
2.2 Example technologies and their impact
Disease Detection and Management
3.1 AI-driven image recognition for early disease detection
3.2 Case Studies
Yield Prediction
4.1 Crop yield prediction
4.2 Benefits for farmers and the supply chain
Soil Health Monitoring
5.1 Examples of technologies and outcomes
Pest Management
6.1 AI systems for early pest detection and control
6.2 Impact on reducing crop damage and pesticide use
Discussion
7.1 Synthesis of how these applications contribute to overall crop management
7.2 Common challenges and limitations
7.3 Potential solutions and areas for improvement
Conclusion
8.1 Summary of the main points discussed
8.2 Key applications of AI in crop management
8.3 Highlighting the potential of AI to transform agriculture
8.4 Suggest areas for future research or development in AI applications
References

Introduction

Imagine a world where farms are managed with the precision and efficiency of a factory floor. This is not science fiction; it is the reality brought about by the integration of artificial intelligence (AI) into agriculture. AI is transforming agriculture, making it more productive, efficient, and sustainable. In this article, we will explore the current applications of AI in crop management and illustrate how these technologies are revolutionizing the agricultural landscape.

Precision Farming

2. 1 Optimizing planting schedules, irrigation, and harvesting

AI is revolutionizing precision farming by optimizing key processes such as planting schedules, irrigation, and harvesting. Machine learning algorithms analyze soil conditions, weather forecasts, and historical data to determine the best planting times, ensuring crops are planted under ideal conditions. This approach significantly increases yields and reduces the risk of crop failure.

One example is the use of machine learning and predictive analytics to determine optimal planting schedules. By analyzing vast amounts of data, these systems can predict the best times to plant different crops, taking into account factors such as soil temperature, moisture levels, and weather forecasts (Elkamel et al., 2022).

Irrigation is another area where AI is having a significant impact. AI-driven smart irrigation systems use sensors and IoT devices to monitor soil moisture levels, weather conditions, and plant water requirements in real-time. These systems apply the exact amount of water needed at the right time, conserving water and improving crop health (Kumar et al., 2023). For example, subsurface water retention technology (SWRT) integrates AI to more effectively manage water distribution by retaining water at the root level. Studies show that AI-optimized SWRT can significantly increase water use efficiency and crop yield (Roy et al., 2019).

Harvesting is also benefiting from advances in AI. Robotic harvesting systems equipped with advanced sensors and computer vision techniques can identify ripe crops and harvest them with high accuracy, lowering labor costs and increasing efficiency (Maraveas, 2022).

2.2 Example technologies and their impact

Satellite imagery and IoT sensors, machine learning models, robotic systems, and precision irrigation systems are key AI technologies in precision agriculture. For example, an AI-based precision farming technology in Italian cereal farms reduced labor costs by 20% and pesticide use by 53% while maintaining crop yields (Bucci et al., 2020). Similarly, an AI-optimized subsurface water retention technology (SWRT) significantly increased water use efficiency and crop yields (Roy et al., 2019).

In China, a precision rice management system using machine learning models increased grain yield by 10% and nitrogen use efficiency by up to 97% compared to traditional practices (Zhao et al., 2013). These examples demonstrate how AI technologies are improving resource use efficiency and crop yields, making agriculture more productive and sustainable.

Disease detection and management

3.1 AI-driven image recognition for early disease detection

AI-driven image recognition technologies are critical for early disease detection. These systems use deep learning models to analyze images of crops and detect diseases at an early stage. This early detection allows for timely intervention and better crop management, ultimately improving crop health and yield.

For example, a deep learning model for tomato leaf disease detection achieved a classification accuracy of 94.1%, allowing for early intervention and better crop management (Annabel & Muthulakshmi, 2019). Similarly, deep learning models trained on large datasets such as PlantVillage have achieved up to 92.54% recognition accuracy, making them suitable for mobile deployment and accessible to farmers in the field (Yuan et al., 2022).

3.2 Case Studies

Successful implementations of AI in disease detection include the use of deep learning models for general crop disease detection and pest detection. For example, a YOLO V5-CAcT model achieved an average detection accuracy of 94.24% across 59 disease categories, making it practical for large-scale agricultural use (Dai & Fan, 2022). Another example is the use of CNN-based detection in robotic vision systems, which demonstrated high accuracy in identifying diseases in crops such as tomatoes and potatoes (Hidayah et al., 2022).

These AI-driven technologies have proven to be highly effective in the early detection of disease in crops, significantly improving disease management and crop yields. By providing timely and accurate diagnoses, these systems help farmers take proactive measures to protect their crops and reduce economic losses.

Yield Prediction

4.1 Crop yield prediction

AI models predict crop yields by analyzing factors such as weather, soil conditions, and historical data. These models use advanced algorithms and data from multiple sources to provide accurate and timely predictions, helping farmers make informed decisions about crop management and resource allocation.

Machine learning models such as linear regression, random forest, and neural networks are used to predict crop yields. These models are trained using historical data on crop yields, weather patterns, and soil characteristics. For example, a machine learning model developed to predict crop yields showed promising results, with a focus on improving the reliability of predictions by comparing different algorithms (Khade et al., 2023).

Deep neural networks (DNNs), particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are also being used to predict crop yields by capturing the complex relationships between environmental factors and crop performance. A DNN model optimized for corn yield prediction under extreme weather conditions demonstrated superior accuracy, outperforming other AI models with a correlation coefficient of 0.954 for drought cases (Kim et al., 2020).

The Agricultural Production Systems sIMulator (APSIM) integrates weather, soil, and management data to simulate crop yield and soil-plant nitrogen dynamics. This model uses historical, current, and forecast weather data to drive simulations and predict corn and soybean yields with high accuracy (Archontoulis et al., 2020).

4.2 Benefits for farmers and the supply chain

Precise yield forecasts improve planning, resource allocation and decision-making for farmers and the agricultural supply chain. For example, AI models help farmers optimize fertilizer and water use, reducing waste and increasing productivity. In Morocco, machine learning algorithms have significantly raised the accuracy of yield predictions, helping farmers make informed decisions about planting schedules and crop selection (Ed-Daoudi et al., 2023).

Efficient resource allocation is another benefit of predictive forecasting. Machine learning models optimize the use of fertilizer, water, and other inputs by providing recommendations based on predicted yields. For example, a hybrid MLR-ANN model for paddy yield prediction in India showed better accuracy than traditional methods, enabling efficient resource allocation and less waste (Maya-GopalP. & Bhargavi, 2019).

Reliable yield predictions also reduce potential losses. Early and timely yield forecasts allow farmers to take proactive measures to mitigate risks such as adverse weather conditions. Improved extreme learning machines (IELMs) with 99.99% accuracy help farmers in India predict yields and reduce potential losses due to unexpected environmental changes (Vashisht et al., 2022).

In the agricultural supply chain, yield forecasts optimize supply chain management by enabling better inventory and logistics planning for agribusinesses and retailers. For example, the use of Random Forests and other machine learning methods has improved yield predictions, helping stakeholders efficiently manage supply chain logistics (Jeong et al., 2016).

Better food security is another important benefit. With precise yield forecasts, policymakers and governments can plan for potential food shortages and effectively manage food reserves. Seasonal climate prediction models combined with satellite data have increased maize yield forecasts in the United States, aiding food security planning and reducing the risk of shortages (Peng et al., 2018).

Correct yield forecasts also contribute to economic stability by stabilizing prices and decreasing market volatility. Yield forecasts provide estimates of crop production levels, helping farmers plan better and reduce costs associated with the overuse of inputs such as water and pesticides. Dynamic factor models for crop yield prediction support better index-based insurance policies, and reduce financial risk for farmers and insurers. (Li et al., 2018).

Soil health monitoring

5.1 AI tools for soil health assessment

AI tools have become critical in assessing and improving soil health by providing real-time, accurate data and predictive insights. These technologies optimize soil management, increasing agricultural productivity and sustainability. Key AI technologies used in soil health assessment include soil health tools, machine learning for nutrient deficiency detection, and virtual soil moisture sensors.

The Soil Health Tool integrates various soil testing methods to assess soil health, including measurements of inorganic nutrients, organic carbon, and microbial activity. The tool provides accurate estimates of plant-available nutrients and overall soil health, leading to superior nutrient management and crop productivity (Haney et al., 2018).

Machine learning models analyze soil nutrient levels, providing real-time data and predictive analytics. Successful applications by Indian startups such as CropIn and Fasal have led to improved crop yields, reduced fertilizer costs, and increased sustainability (Ashoka et al., 2023).

Virtual soil moisture sensors use deep learning models, specifically LSTM networks, to estimate soil moisture from other sensor data. This approach provides soil moisture data that allows for better irrigation management and increases soil productivity (Patrizi et al., 2022).

5.2 Examples of technologies and outcomes

AI-based nutrient deficiency detection systems have improved crop yields and reduced fertilizer costs. Virtual soil moisture sensors provide accurate data for better irrigation management, while IoT-based agro-toolboxes effectively monitor soil health parameters, enabling precise agricultural practices.

An IoT-based agro-toolbox integrates various sensors to monitor soil pH, moisture, temperature, and environmental conditions. This toolbox has demonstrated effective soil health monitoring, enabling precise agricultural practices with acceptable error rates (Pechlivani et al., 2023).

Sensor data fusion combines VNIR spectroscopy, soil electrical conductivity, and penetration resistance data to assess soil health. This method improves the accuracy of soil health indicators and Soil Management Assessment Framework (SMAF) scores, demonstrating the potential for rapid quantification of soil health (Veum et al., 2017).

Infrared spectroscopy, combined with machine learning models, is another advanced technique used to assess soil health. This technique enables rapid and robust prediction of soil health indicators, making it accessible for routine use in soil laboratories (Deiss et al., 2021).

In addition, AI-driven soil health monitoring systems integrate AI with IoT sensors to monitor soil parameters such as pH, moisture, and nutrient levels. These systems help farmers make informed decisions about irrigation, fertilization, and crop management, leading to improved soil health and higher crop yields (Deorankar & Rohankar, 2020).

Long-term biosolids application is another area where AI is making a difference.AI evaluated the impact of long-term biosolids application on soil health and found that biosolids significantly increased soil chemical and biological health indices, enhancing soil fertility and crop production (Ippolito et al., 2021).

Overall, AI applications in soil health monitoring are transforming agricultural practices by providing real-time data and predictive insights. These technologies are improving soil management, leading to increased crop yields, reduced resource use, and sustainable agriculture.

Pest Management

6.1 AI systems for early pest detection and control

AI systems for early pest detection and control are revolutionizing agricultural practices by enabling precise, real-time monitoring and management of pest populations. These technologies use advanced algorithms, sensor networks and image recognition to effectively identify and manage pests, improving crop health and limiting economic losses.

AI pest detection systems use image recognition and machine learning algorithms to detect pests. Cameras capture images of crops, which are then analyzed by convolutional neural networks (CNNs) or other deep learning models to identify pests. For example, an AIoT-based system using YOLOv3 for image recognition and LSTM for environmental data analysis achieved 90% accuracy in pest identification, enabling precise pesticide application and reducing pesticide use (Chen et al., 2020).

Acoustic detection is another innovative approach in which AI models analyze audio signals to detect pests. It uses sound sensors and deep learning techniques to classify and identify the presence of pests based on their acoustic signatures. An AI-based pest detection model using sound sensors and neural networks can detect and categorize pests and alert farmers via mobile notifications (Thomas et al., 2023).

Unmanned aerial vehicles (UAVs) equipped with cameras and sensors also play a critical role in pest detection. UAVs fly over fields to capture images and audio that are then processed by AI models to detect pests. For example, the PEDS-AI system uses UAVs to achieve a precision of 0.92 and a recall of 0.84 in detecting locusts, significantly improving pest monitoring in fields (Zhang, 2023).

IoT and sensor networks further enhance pest detection by collecting environmental data through various sensors (e.g., infrared, humidity, temperature). AI models use this data to predict pest outbreaks and suggest timely interventions. A smart agricultural system using IoT and AI for pest detection showed significant improvements in early detection and reduced pesticide damage (Blanco-Carmona et al., 2023).

6.2 Impact on reducing crop damage and pesticide use

AI-driven pest detection systems significantly improve the accuracy of pest detection compared to traditional methods. For example, a neural classifier system for potato and bean crops achieved an 89% detection rate for pests such as the Colorado potato beetle (Roldán-Serrato et al., 2018). Early detection allows growers to take timely action, which reduces crop loss and minimizes the need for widespread pesticide use.

Lower pesticide use is a major benefit of AI-based pest management systems. Pest identification enables targeted pesticide application, reducing overall chemical usage. For example, AIoT systems for pest detection have been shown to reduce pesticide use by targeting specific areas and times for application (Chen et al., 2020). This results in lower production costs, reduced environmental impact, and healthier crops.

Real-time monitoring and alerts from AI systems enable immediate action. An AI-based pest detection system that uses IoT for real-time monitoring can notify farmers about the presence of pests via mobile apps, helping them to proactively manage infestations (Thomas et al., 2023). This increases the efficiency of pest management practices and reduces labor costs.

Discussion

7.1 Synthesis of how these applications contribute to overall crop management

Collectively, AI technologies improve crop management by optimizing planting schedules, irrigation, soil health, pest management, and yield prediction. These advances lead to improved productivity, sustainability, and efficiency in agriculture.

Optimizing planting schedules with AI ensures that crops are planted under ideal conditions, increasing yields and reducing the risk of crop failure (Elkamel et al., 2022). AI-driven smart irrigation systems optimize water use, conserve resources, and improve crop health by delivering the precise amount of water needed (Kumar et al., 2023).

AI tools for soil health assessment provide accurate estimates of soil nutrients, leading to improved nutrient management and crop productivity (Haney et al., 2018). Early disease detection using AI-powered image recognition and machine learning models enables timely intervention, reduces crop losses, and minimizes the use of fungicides and other chemicals (Yuan et al., 2022).

AI systems for pest detection use image recognition, acoustic detection, and UAVs to identify and manage pests, reducing pesticide use, lowering production costs, and protecting beneficial insects. This results in healthier crops and improved environmental sustainability (Pecenka et al., 2021).

Accurate yield predictions provided by AI models help farmers make informed decisions about resource allocation, planting schedules, and market strategies, ultimately increasing productivity and profitability (Khade et al., 2023).

7.2 Common challenges and limitations

Despite its potential, AI in agriculture faces several challenges and limitations. Addressing these challenges is critical to fully harnessing the capabilities of AI to improve agricultural productivity and sustainability.

Data quality and availability are key issues. Inconsistent and poor-quality data can hinder the effectiveness of AI models. Variability in data collection methods, formats, and sources leads to difficulties in integrating and analyzing data comprehensively (Linaza et al., 2021).

Connectivity and infrastructure limitations, especially in rural areas, also pose challenges. The lack of reliable internet connectivity and digital infrastructure limits the adoption of AI technologies (Leong et al., 20–23).

The high cost of AI technology and implementation creates barriers for small and medium enterprises. The cost of AI-powered equipment and systems, such as robotic harvesters or precision irrigation systems, can be prohibitive for smaller farms, limiting widespread adoption (Raikov & Abrosimov, 2022).

User adoption and skills gaps are additional barriers. Farmers may lack the technical skills necessary to effectively operate and maintain AI systems. Successful adoption of AI technologies requires training and support to ensure that farmers can use these tools effectively (Sood et al., 2021).

Privacy and security concerns regarding the collection and use of data in AI systems also need to be addressed. Farmers may be reluctant to adopt AI technologies due to fears of data breaches or misuse of their data, which can undermine trust in these systems (Gupta et al., 2020).

7.3 Potential solutions and areas for improvement

Enhancing data quality and standardization is critical. Developing standardized protocols for data collection and management ensures high-quality, consistent data. Implementing standardized data formats and collection methods can increase the reliability and integration of data from disparate sources, improving the performance of AI models (Linaza et al., 2021).

Improving connectivity and infrastructure in rural areas is another critical step. Investing in improving internet connectivity and digital infrastructure can enable the deployment of AIoT systems and other AI technologies in underserved regions (Leong et al., 2023).

Reducing the cost and increasing the accessibility of AI solutions through financial support or subsidies for small and medium-sized enterprises can help overcome economic barriers. Government programs and public-private partnerships can help subsidize the cost of AI technologies, making them more accessible to smaller farms (Raikov & Abrosimov, 2022).

Providing comprehensive training programs and ongoing support for farmers is critical to improving user adoption and closing skills gaps. Establishing training centers and online resources can help farmers acquire the necessary skills to effectively use AI technologies (Sood et al., 2021).

Ensuring data privacy and security by implementing robust measures to protect farmers’ data can build trust among farmers and encourage the adoption of AI technologies (Gupta et al., 2020).

Conclusion

8.1 Summary of the main points discussed

AI technologies are revolutionizing crop management by optimizing planting schedules, irrigation, soil health, pest management, and yield prediction. These advances are leading to improved productivity, sustainability, and efficiency in agriculture.

8.2 Key applications of AI in crop management include

Optimizing planting schedules with machine learning algorithms to ensure crops are planted under ideal conditions.
AI-driven intelligent irrigation systems that optimize water use, conserve resources, and improve crop health.
AI soil health assessment tools that provide a reliable estimate of soil nutrients, leading to improved nutrient management and crop productivity.
Early disease detection using AI-powered image recognition and machine learning models, enabling timely intervention and mitigating crop loss.
AI pest detection systems that use image recognition, acoustic detection, and UAVs to identify and manage pests, decrease pesticide use, and protect beneficial insects.
Precise yield predictions from AI models that help growers make informed decisions about resource allocation, planting schedules, and market strategies.

8.3 Highlighting the potential of AI to transform agriculture

AI has the potential to revolutionize agriculture by increasing productivity, sustainability, and efficiency. The integration of AI technologies can address critical challenges in modern agriculture, such as optimizing resource use, improving crop yields, and reducing environmental impact. AI enables precise monitoring and management of crops, leading to optimized use of inputs (water, fertilizers, pesticides) and improved yields. Technologies such as AI-powered drones and satellite imagery can provide real-time data on crop health and soil conditions.

AI-powered robots and autonomous machines can perform tasks such as planting, weeding, and harvesting, cutting labor costs and increasing efficiency. These technologies can operate around the clock, increasing productivity.

AI models can predict weather patterns, pest outbreaks, and the spread of disease, allowing farmers to take proactive measures. Improved yield forecasts help farmers plan better and make informed decisions about resource allocation and market strategies.

AI-driven systems promote sustainable agriculture by minimizing the use of water, fertilizers, and pesticides, thereby reducing environmental impact. AI-driven systems can optimize resource use and improve soil health, leading to long-term agricultural sustainability.

8.4 Suggest areas for future research or development in AI applications

Future research and development should focus on

Advanced AI algorithms: Developing more sophisticated AI algorithms that can handle the complexity and variability of agricultural environments.
Edge computing: Explore the use of edge computing to process data locally on farms, reducing latency and improving the efficiency of AI systems.
Interoperability and Standards: Promoting interoperability and standardization of data formats and protocols to facilitate seamless integration of AI technologies across platforms and devices.
Climate Resilience: Exploring the role of AI in the development of climate-resilient agricultural practices and crops.
Adoption and Usability: Improving the adoption and usability of AI technologies among farmers, especially small and medium-sized farms.
Social and ethical implications: Addressing the social and ethical implications of AI in agriculture, such as privacy, security, and the impact on farm labor.
AI-driven supply chain integration: Exploring the integration of AI technologies throughout the agricultural supply chain, from farm to market.
Robotics and Autonomous Systems: Invest in the development of advanced robotics and autonomous systems for agriculture.

By addressing these areas, AI can play a pivotal role in shaping the future of agriculture and ensuring global food security.

References

Annabel, L., & Muthulakshmi, V. (2019). AI-Powered Image-Based Tomato Leaf Disease Detection. 2019 Third International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), 506–511. https://doi.org/10.1109/I-SMAC47947.2019.9032621.
Archontoulis, S., Castellano, M., Licht, M., Nichols, V., Baum, M., Huber, I., Martinez-Feria, R., Puntel, L., Ordóñez, R., Iqbal, J., Wright, E., Dietzel, R., Helmers, M., VanLoocke, A., Liebman, M., Hatfield, J., Herzmann, D., Córdova, S., Edmonds, P., Togliatti, K., Kessler, A., Danalatos, G., Pasley, H., Pederson, C., & Lamkey, K. (2020). Predicting crop yields and soil‐plant nitrogen dynamics in the US Corn Belt. Crop Science, 60, 721–738. https://doi.org/10.1002/csc2.20039.
Ashoka, P., Avinash, G., Apoorva, M., Raj, P., Sekhar, M., Singh, S., Kumar, R., & Singh, B. (2023). Efficient Detection of Soil Nutrient Deficiencies through Intelligent Approaches. BIONATURE. https://doi.org/10.56557/bn/2023/v43i21877.
Blanco-Carmona, P., Baeza-Moreno, L., Hidalgo-Fort, E., Martín-Clemente, R., González-Carvajal, R., & Muñoz-Chavero, F. (2023). AIoT in Agriculture: Safeguarding Crops from Pest and Disease Threats. Sensors (Basel, Switzerland), 23. https://doi.org/10.3390/s23249733.
Bucci, G., Bentivoglio, D., Belletti, M., & Finco, A. (2020). Measuring a farm’s profitability after adopting precision agriculture technologies: A case study from Italy. , 9, 65. https://doi.org/10.21014/ACTA_IMEKO.V9I3.799.
Chen, C., Huang, Y., Li, Y., Chang, C., & Huang, Y. (2020). An AIoT-Based Smart Agricultural System for Pests Detection. IEEE Access, 8, 180750–180761. https://doi.org/10.1109/ACCESS.2020.3024891.
Dai, G., & Fan, J. (2022). An Industrial-Grade Solution for Crop Disease Image Detection Tasks. Frontiers in Plant Science, 13. https://doi.org/10.3389/fpls.2022.921057.
Deiss, L., Oottikkal, S., Tomko, K., Huang, W., Culman, S., & Demyan, S. (2021). Machine learning to automate rapid soil health assessment using infrared spectroscopy. . https://doi.org/10.5194/ismc2021-83.
Deorankar, A., & Rohankar, A. (2020). Soil Health Monitoring System using AI. Journal of emerging technologies and innovative research.
Ed-Daoudi, R., Alaoui, A., Ettaki, B., & Zerouaoui, J. (2023). Improving Crop Yield Predictions in Morocco Using Machine Learning Algorithms. Journal of Ecological Engineering. https://doi.org/10.12911/22998993/162769.
Elkamel, M., Rabelo, L., & Wang, M. (2022). Machine Learning Models for Crop Yield Prediction and a Smart Irrigation System. Proceedings of the International Conference on Industrial Engineering and Operations Management. https://doi.org/10.46254/na07.20220426.
Gupta, N., Gupta, P., Nadeem, D., A, A., & Elahi, A. (2020). Artificial Intelligence in Agriculture. Journal of Physics: Conference Series, 1693. https://doi.org/10.1088/1742-6596/1693/1/012058.
Haney, R. L., Haney, E. B., Smith, D. R., Harmel, R. D., & White, M. J. (2018). The soil health tool — Theory and initial broad-scale application. Applied Soil Ecology, 125, 162–168. https://doi.org/10.1016/j.apsoil.2017.07.035
Hidayah, A., Radzi, S., Razak, N., Saad, W., Wong, Y., & Naja, A. (2022). Disease Detection of Solanaceous Crops Using Deep Learning for Robot Vision. Journal of Robotics and Control (JRC). https://doi.org/10.18196/jrc.v3i6.15948.
Ippolito, J., Ducey, T., Diaz, K., & Barbarick, K. (2021). Long-term biosolids land application influences soil health.. The Science of the total environment, 791, 148344 . https://doi.org/10.1016/J.SCITOTENV.2021.148344.
Jeong, J., Resop, J., Mueller, N., Fleisher, D., Yun, K., Butler, E., Timlin, D., Shim, K., Gerber, J., Reddy, V., & Kim, S. (2016). Random Forests for Global and Regional Crop Yield Predictions. PLoS ONE, 11. https://doi.org/10.1371/journal.pone.0156571.
Khade, S., Malaye, V., Mhase, S., Shitole, A., & Shirsath, P. (2023). Crop Yield Prediction Using Machine Learning. International Journal of Advanced Research in Science, Communication and Technology. https://doi.org/10.48175/ijarsct-8584.
Kim, N., Na, S., Park, C., Huh, M., Oh, J., Ha, K., Cho, J., & Lee, Y. (2020). An Artificial Intelligence Approach to Prediction of Corn Yields under Extreme Weather Conditions Using Satellite and Meteorological Data. Applied Sciences. https://doi.org/10.3390/app10113785.
Kumar, J., Chawla, R., Katiyar, D., Chouriya, A., Nath, D., Sahoo, S., Ali, A., & Singh, B. (2023). Optimizing Irrigation and Nutrient Management in Agriculture through Artificial Intelligence Implementation. International Journal of Environment and Climate Change. https://doi.org/10.9734/ijecc/2023/v13i103077.
Leong, Y., Lim, E., Subri, N., & Jalil, N. (2023). Transforming Agriculture: Navigating the Challenges and Embracing the Opportunities of Artificial Intelligence of Things. 2023 IEEE International Conference on Agrosystem Engineering, Technology & Applications (AGRETA), 142–147. https://doi.org/10.1109/AGRETA57740.2023.10262747.
Li, H., Porth, L., Tan, K., & Zhu, W. (2018). Improved Index Insurance Design and Yield Estimation Using a Dynamic Factor Forecasting Approach. Agricultural Food Science. https://doi.org/10.2139/ssrn.3195396.
Linaza, M., Posada, J., Bund, J., Eisert, P., Quartulli, M., Döllner, J., Pagani, A., Olaizola, I., Barriguinha, A., Moysiadis, T., & Lucat, L. (2021). Data-Driven Artificial Intelligence Applications for Sustainable Precision Agriculture. Agronomy. https://doi.org/10.3390/agronomy11061227.
Maraveas, C. (2022). Incorporating Artificial Intelligence Technology in Smart Greenhouses: Current State of the Art. Applied Sciences. https://doi.org/10.3390/app13010014.
MayaGopalP., S., & Bhargavi, R. (2019). A novel approach for efficient crop yield prediction. Comput. Electron. Agric., 165. https://doi.org/10.1016/J.COMPAG.2019.104968.
Patrizi, G., Bartolini, A., Ciani, L., Gallo, V., Sommella, P., & Carratù, M. (2022). A Virtual Soil Moisture Sensor for Smart Farming Using Deep Learning. IEEE Transactions on Instrumentation and Measurement, 71, 1–11. https://doi.org/10.1109/tim.2022.3196446.
Pechlivani, E., Papadimitriou, A., Pemas, S., Ntinas, G., & Tzovaras, D. (2023). IoT-Based Agro-Toolbox for Soil Analysis and Environmental Monitoring. Micromachines, 14. https://doi.org/10.3390/mi14091698.
Peng, B., Guan, K., Pan, M., & Li, Y. (2018). Benefits of Seasonal Climate Prediction and Satellite Data for Forecasting U.S. Maize Yield. Geophysical Research Letters, 45, 9662–9671. https://doi.org/10.1029/2018GL079291.
Raikov, A., & Abrosimov, V. (2022). Artificial Intelligence and Robots in Agriculture. 2022 15th International Conference Management of large-scale system development (MLSD), 1–5. https://doi.org/10.1109/MLSD55143.2022.9934170.
Roldán-Serrato, K. L., Escalante-Estrada, J., & Rodríguez-González, M. (2018). Automatic pest detection on bean and potato crops by applying neural classifiers. Engineering in Agriculture, Environment and Food, 11(4), 245–255. https://doi.org/10.1016/j.eaef.2018.08.003
Roy, P., Guber, A., Abouali, M., Nejadhashemi, A., Deb, K., & Smucker, A. (2019). Crop yield simulation optimization using precision irrigation and subsurface water retention technology. Environ. Model. Softw., 119, 433–444. https://doi.org/10.1016/J.ENVSOFT.2019.07.006.
Sood, A., Sharma, R., & Bhardwaj, A. (2021). Artificial intelligence research in agriculture: a review. Online Inf. Rev., 46, 1054–1075. https://doi.org/10.1108/oir-10-2020-0448.
Thomas, J., Manikandarajan, S., & Subha, T. (2023). AI-based pest detection and alert system for farmers using IoT. E3S Web of Conferences. https://doi.org/10.1051/e3sconf/202338705003.
Vashisht, S., Kumar, P., & Trivedi, M. (2022). Crop Yield Prediction Using Improved Extreme Learning Machine. Communications in Soil Science and Plant Analysis, 54, 1–21. https://doi.org/10.1080/00103624.2022.2108828.
Veum, K., Sudduth, K., Kremer, R., & Kitchen, N. (2017). Sensor data fusion for soil health assessment. Geoderma, 305, 53–61. https://doi.org/10.1016/J.GEODERMA.2017.05.031.
Yuan, S., Luo, X., & Xu, R. (2022). Crop disease recognition based on deep learning. 2022 9th International Conference on Digital Home (ICDH), 61–66. https://doi.org/10.1109/icdh57206.2022.00017.
Zhang, R. (2023). PEDS-AI: A Novel Unmanned Aerial Vehicle Based Artificial Intelligence Powered Visual-Acoustic Pest Early Detection and Identification System for Field Deployment and Surveillance. 2023 IEEE Conference on Technologies for Sustainability (SusTech), 12–19. https://doi.org/10.1109/SusTech57309.2023.10129631.
Zhao, G., Miao, Y., Wang, H., Su, M., Fan, M., Zhang, F., Jiang, R., Zhang, Z., Liu, C., Liu, P., & Ma, D. (2013). A preliminary precision rice management system for increasing both grain yield and nitrogen use efficiency. Field Crops Research, 154, 23–30. https://doi.org/10.1016/J.FCR.2013.07.019.