April 3, 2025
•
10 min
read
Don’t worry: computers are not a threat to your work… yet 😈 AI is still far from mastering the complexity and creativity of agricultural research. We can see three major changes in crop science1:
• More complex agronomic protocols are needed to account for factors impacting the crops in the context of climate change
• More comprehensive data on crop phenotype, genotype, and environmental factors
• More data-driven decisions
Data management takes up more space in the daily tasks of agronomists. Fortunately machine learning excels at managing data. These artificial intelligence methods assist crop scientists by streamlining complex data tasks. With the right tools, they can plan multi-location agronomy trials, measure and standardize plant and environmental traits, and analyze all this data2. In particular, AI accelerates plant breeding through smart data analysis3. It helps predict crop performance by optimizing selection based on biotic and abiotic risks, such as soil and water management4.
"Scientists, in particular, want to fully understand their tools. What if AI is biased toward drawing certain conclusions, and that bias initially goes unnoticed?" says Dr. Bas van der Velden, team leader of Data Science at Wageningen Food Safety Research (WFSR)5.
Then what can you expect from the development of artificial intelligence in your crop innovation department? Let’s see some use cases of useful AI integration and discuss the outcome for your job in crop sciences.
Use Cases of AI Technologies in Crop Innovation
1. AI Enhances data accuracy with outlier detection
2. AI Empowers High-Throughput Phenotyping
3. Enhancing Plant Breeding Through Performance Prediction in a New Environment
4. From Data Chaos to Clarity: Generative AI in Crop Innovation
Prerequisites for using Artificial Intelligence in crop innovation
1. Integrate standardized data
⨠ What makes a breeding or agronomy database ready for AI ?
2. Difficulties to adopt machine learning
Conclusion: The Future of AI in Agricultural Research: Driving Crop Innovation and Sustainability
In agricultural research, accurate data is crucial. Anomalies— such as faulty sensor readings or data entry mistakes— can lead to misleading results and poor decisions in breeding and irrigation strategies. Fortunately, machine learning is transforming the way crop scientists detect and handle these irregularities.
Djampa, a data analyst at Doriane, explains: “We’re integrating machine learning into Bloomeo to detect outliers during both data acquisition and processing. Bloomeo leverages AI to identify inconsistencies at different stages of experimentation, ensuring the integrity of research data.”
Machine learning takes the guesswork out of spotting anomalies, making it possible to sift through vast datasets efficiently. Doriane is at the forefront of machine learning integration to enhance data quality. We streamline research processes by facilitating data validation at scale.
Key Steps in AI-Driven Data Validation:
1. Early Detection: For small datasets, statistical methods like the Interquartile Range (IQR) flag inconsistencies. For large datasets, advanced clustering techniques such as DBSCAN and Isolation Forest uncover hidden patterns.
2. Human Feedback Loop: Researchers review flagged data, which gradually refines the AI model from semi-supervised to fully supervised learning.
3. Continuous Monitoring: Bloomeo’s algorithms work in real time to maintain data quality. Future enhancements will expand detection to time-series data, like weather fluctuations, for more accurate results.
By integrating AI into crop innovation, researchers can focus on valuable insights rather than correcting errors. With AI-powered tools like Bloomeo field trial software, agricultural research becomes more precise, efficient, and reliable.
Understanding crop performance in the field is like decoding nature’s blueprint. Traditional methods rely on observation, but modern research departments take it further with high-throughput phenotyping (HTP)—using sensors, cameras, and drones to collect massive amounts of plant data. The challenge? Making sense of it all. That’s where AI steps in.
AI processes huge datasets at lightning speed, detecting patterns that would take humans much longer to uncover. Machine learning models analyze plant traits like leaf structure, height, and disease symptoms in real time, helping researchers breed stronger crops and improve stress resistance.
One standout in this field is Hiphen, a company specializing in AI-driven image analysis for agricultural research. Their technology transforms raw images into actionable insights, helping scientists make precise, data-driven decisions.
A key innovation from Hiphen is their model drifting dashboard, which ensures AI models remain accurate as conditions change. This monitoring tool detects shifts in model performance, helping researchers fine-tune their algorithms over time.
By combining AI with high-throughput phenotyping, researchers can work faster and smarter. Automated trait measurement speeds up plant breeding, improves disease resistance studies, and refines agronomy trials.
AI isn’t here to replace crop scientists; it’s here to empower them. With tools like Hiphen’s technology, researchers can push the boundaries of crop innovation, making smarter, more sustainable decisions for the future of agriculture.
According to Hiphen, “AI has brought revolutionary changes to agriculture, increasing efficiency, precision, and productivity. However, it complements human expertise rather than replacing it.”
AI is transforming plant breeding, particularly in predicting how a genotype will perform in diverse environments. Imagine you're a plant breeder with a promising new hybrid. Before testing it across different soil types, climates, and regions, you need insights on where it will thrive. By training AI models on historical hybrid data—considering past performances under various conditions—researchers can now predict how new hybrids will behave in different environments.6
• Predictive Model Generation: AI-powered models analyze genetic, phenotypic, and environmental data to forecast which plant traits will perform best in specific locations. Breeders benefit from defining ideal crop profiles for a given area: This targeted approach saves time by narrowing down the best progenies to test in that environment.
• Phenotypic prediction to optimize resources: Through AI-driven simulations, researchers can model crop growth in various conditions to understand how plants may adapt to new environments. This accelerates breeding cycles, allowing breeders to make informed decisions with fewer field tests.
Plant breeders traditionally spend years assessing crop performance across different locations. AI expands their decision-making capabilities by providing data-driven insights, reducing risks, and offering deeper segmentation criteria for selection.7
At Doriane, machine learning is used to uncover complex relationships within phenotypic, genetic, and environmental datasets. Our digital platform empowers researchers to predict crop performance and enhance selection accuracy.
In collaboration with RAGT, AI researcher Rony Charles successfully developed a neural network model to predict corn hybrid performance under specific soil, weather, and field conditions.8
He explains: “A notable example is the collaboration with RAGT, where a neural network model was developed to predict the suitability of hybrid corn for specific growing conditions with 95% accuracy. This model helps plant breeders make informed decisions, ensuring that new crop varieties are well-adapted to their environments.”
By leveraging AI, plant breeding becomes faster, more efficient, and better tailored to the challenges of modern agriculture. With AI-assisted predictions, researchers can accelerate innovation, improve crop resilience, and ultimately, cultivate a more sustainable future.9
Read the full report: AI in agriculture research.
The integration of generative AI into the ideation process for crop science research could transform the way scientists develop new processes, design experiments, and explore new agricultural solutions.
We've heard about customers beginning to use generative AI in brainstorming sessions within a multi-disciplined breeding team. The idea is simple: bring a language model like ChatGPT to the table alongside agronomists, data scientists, and biologists, to explore the potential outcomes.
"We started using OpenAI during some trait-brainstorming meetings—more out of curiosity than expectation,” explains an R&D director. “We input trial results, weather patterns, soil profiles, and sensor-derived omics data.”
The result? AI-generated suggestions that sometimes stretch beyond current feasibility, but often reveal unexplored avenues or unexpected trait interactions. While not all proposals are actionable, some have sparked innovative pilot studies that would not have emerged from traditional discussions alone.
In this context, generative AI acts like a tireless colleague—one who draws connections across disciplines and isn’t limited by conventional thinking. It raises questions, suggests alternatives, and helps uncover blind spots.
Beyond brainstorming, generative models have been used to contribute to scientific discussions. For instance, in the ongoing project “One Hundred Important Questions Facing Plant Science”, generative AI was able to generate complementary questions that had not yet been raised by the human panel of experts 10.
.webp)
Creating effective AI tools for agriculture involves more than just implementing algorithms. Successful integration of AI into agriculture research requires a deep understanding of the domain, access to high-quality datasets, and collaboration between technologists and agricultural experts.
Machine learning tools justify their value on large datasets, and various data types, but they still need to offer intuitive user interfaces that allow researchers to apply them effectively. Data integration across different research areas, such as crop genetics, envirotyping, and agronomy, is critical for the success of AI tools in agricultural research.
Combining phenotypic, genotypic, and environmental data offers a holistic view that enhances decision-making in crop research. This organized data structure is essential for enabling AI.
For AI to deliver its full potential in plant breeding and agronomy testing, effective data management is essential. AI technologies rely on massive datasets, to make predictions and recommendations.
Doriane brings all its expertise to facilitate AI adoption and make AI projects easier for data scientists.
Djampa, a data scientist at Doriane : “Currently 70% of the effort in an AI algorithm development project is done on structuring datasets then choosing models and training them is the fun part of the project” This integration makes AI more effective, providing valuable insights that were previously inaccessible.
One major challenge is change management. Machine learning relies on structured data. Setting up the correct parameters from the start is crucial to ensure valid and useful statistics. This extends the role of data analysts to define and ensure these parameters, rather than relying on a handover between technicians who may not align with the necessary standards. Crop innovation companies typically invest around 20% of their revenue in R&D on average, but, in a market where money is tight, there is less room for delays and waste. Every step must be efficient and precise, especially in a business where it takes 10 years to get a new variety in the market.
Moreover, change management can be particularly challenging in innovation teams. For instance, intuitive plant breeders with historical expertise may resist the data-driven approaches of the new generation of plant breeders. This resistance to change can slow down the adoption of new technologies. Overcoming this requires strong leadership, clear communication about the benefits, and a collaborative approach to integrating new methods with traditional expertise.
At Doriane, we assist clients in adopting machine learning by helping them establish clear data frameworks.
No model can fully replace domain knowledge and intuition. In your job as a crop scientist, AI can help you save time, conserve resources, and make better decisions—but it cannot replace your experience, your creativity, and your understanding of research objectives.
And there's so much to explore with AI: Some data scientists even say that the first level of AI includes tools like calculators or regression analysis. Use cases such as deep learning and machine learning for predictive analysis are already widely adopted by some companies.
We're entering a new chapter—finding meaningful applications for generative AI tools like ChatGPT. The challenge is to identify how these can be applied meaningfully in agriculture innovation.
At Doriane we are exploring such technologies to improve the user experience for breeders and agronomists on our platforms. Machine learning models rely on user feedback to continually learn and improve. While machine learning can provide relevant recommendations, final validation depends on rigorous experimentation by crop scientists, following established statistical standards.
AI isn’t just about making predictions; it's about unlocking the future of agriculture:
Doriane’s expertise in managing and analyzing agronomic data, combined with the use of machine learning and public data repositories, is driving major progress in crop innovation. Learn more on our "Your Project" page
As AI continues to evolve, it has a key role to play in the development of resilient crops that excel in challenging conditions such as saline soils, extreme heat, drought, and biotic stress. This approach supports global food security, promotes biodiversity, reduces dependency on chemical inputs, and helps ensure sustainable farming practices in the face of environmental challenges.
Source:
1. Davison, A. "AI and the Futureof Agriculture." IBM Think Blog, 24 September 2024.
2. Alam, A. "Perspectives onArtificial Intelligence in Agriculture." Current Agriculture ResearchJournal, vol. 12, no. 1, 2024.
3. Rai, K.K. "IntegratingSpeed Breeding with Artificial Intelligence for Developing Climate-SmartCrops." Molecular Biology Reports, vol. 49, 2022, pp. 11385–11402.
4. Ali, Zulfiqar, Asif Muhammad,Nangkyeong Lee, Muhammad Waqar, and Seung Won Lee. 2025. "ArtificialIntelligence for Sustainable Agriculture: A Comprehensive Review of AI-DrivenTechnologies in Crop Production" Sustainability 17, no. 5: 2281.
5. Wageningen University &Research. "Artificial Intelligence." WUR Research Themes, 2025.
6. Authors Unknown."Assessing Environment Types for Maize, Soybean, and Wheat in the UnitedStates." Field Crops Research, vol. 270, 2021, p. 108198.
7. Bose, S., Banerjee, S., Kumar,S., Saha, A., Nandy, D., & Hazra, S. "Review of Applications ofArtificial Intelligence (AI) Methods in Crop Breeding." Journal of PlantGenomics, vol. 12, no. 4, 2023, pp. 567–589.
8. DanielWallach, Pierre Martre, Bo Liu, Senthold Asseng, Frank Ewert, et al.. Multi-model ensembles improve predictions ofcrop-environment-management interactions. Global Change Biology, 2018, 24 (11),pp.5072-5083.
9. Rony, A. "TitleUnknown." HAL Archives, Document ID: hal-02625468.
10. Muhammad Amjad Farooq et al., Artificial intelligence in plant breeding, Trends in Genetics, Volume 40, Issue 10, 2024, Pages 891-908, ISSN 0168-9525.
11. McKinsey & Company. "From Bytes to Bushels: How GenerativeAI Can Shape the Future of Agriculture." McKinsey & Company, 2024.
Did you find this article useful? Share it!
Webinar Replay
Next webinar
April 24, 2025
Unlock the power of multi-factorial trials! Learn from our agronomist and IT expert to design, test, and analyze interaction effects for smarter crop research.
Patricija Levickaite
IT expert & Agronomy engineer
April 3, 2025
•
10 min
read
Don’t worry: computers are not a threat to your work… yet 😈 AI is still far from mastering the complexity and creativity of agricultural research. We can see three major changes in crop science1:
• More complex agronomic protocols are needed to account for factors impacting the crops in the context of climate change
• More comprehensive data on crop phenotype, genotype, and environmental factors
• More data-driven decisions
Data management takes up more space in the daily tasks of agronomists. Fortunately machine learning excels at managing data. These artificial intelligence methods assist crop scientists by streamlining complex data tasks. With the right tools, they can plan multi-location agronomy trials, measure and standardize plant and environmental traits, and analyze all this data2. In particular, AI accelerates plant breeding through smart data analysis3. It helps predict crop performance by optimizing selection based on biotic and abiotic risks, such as soil and water management4.
"Scientists, in particular, want to fully understand their tools. What if AI is biased toward drawing certain conclusions, and that bias initially goes unnoticed?" says Dr. Bas van der Velden, team leader of Data Science at Wageningen Food Safety Research (WFSR)5.
Then what can you expect from the development of artificial intelligence in your crop innovation department? Let’s see some use cases of useful AI integration and discuss the outcome for your job in crop sciences.
Use Cases of AI Technologies in Crop Innovation
1. AI Enhances data accuracy with outlier detection
2. AI Empowers High-Throughput Phenotyping
3. Enhancing Plant Breeding Through Performance Prediction in a New Environment
4. From Data Chaos to Clarity: Generative AI in Crop Innovation
Prerequisites for using Artificial Intelligence in crop innovation
1. Integrate standardized data
⨠ What makes a breeding or agronomy database ready for AI ?
2. Difficulties to adopt machine learning
Conclusion: The Future of AI in Agricultural Research: Driving Crop Innovation and Sustainability
In agricultural research, accurate data is crucial. Anomalies— such as faulty sensor readings or data entry mistakes— can lead to misleading results and poor decisions in breeding and irrigation strategies. Fortunately, machine learning is transforming the way crop scientists detect and handle these irregularities.
Djampa, a data analyst at Doriane, explains: “We’re integrating machine learning into Bloomeo to detect outliers during both data acquisition and processing. Bloomeo leverages AI to identify inconsistencies at different stages of experimentation, ensuring the integrity of research data.”
Machine learning takes the guesswork out of spotting anomalies, making it possible to sift through vast datasets efficiently. Doriane is at the forefront of machine learning integration to enhance data quality. We streamline research processes by facilitating data validation at scale.
Key Steps in AI-Driven Data Validation:
1. Early Detection: For small datasets, statistical methods like the Interquartile Range (IQR) flag inconsistencies. For large datasets, advanced clustering techniques such as DBSCAN and Isolation Forest uncover hidden patterns.
2. Human Feedback Loop: Researchers review flagged data, which gradually refines the AI model from semi-supervised to fully supervised learning.
3. Continuous Monitoring: Bloomeo’s algorithms work in real time to maintain data quality. Future enhancements will expand detection to time-series data, like weather fluctuations, for more accurate results.
By integrating AI into crop innovation, researchers can focus on valuable insights rather than correcting errors. With AI-powered tools like Bloomeo field trial software, agricultural research becomes more precise, efficient, and reliable.
Understanding crop performance in the field is like decoding nature’s blueprint. Traditional methods rely on observation, but modern research departments take it further with high-throughput phenotyping (HTP)—using sensors, cameras, and drones to collect massive amounts of plant data. The challenge? Making sense of it all. That’s where AI steps in.
AI processes huge datasets at lightning speed, detecting patterns that would take humans much longer to uncover. Machine learning models analyze plant traits like leaf structure, height, and disease symptoms in real time, helping researchers breed stronger crops and improve stress resistance.
One standout in this field is Hiphen, a company specializing in AI-driven image analysis for agricultural research. Their technology transforms raw images into actionable insights, helping scientists make precise, data-driven decisions.
A key innovation from Hiphen is their model drifting dashboard, which ensures AI models remain accurate as conditions change. This monitoring tool detects shifts in model performance, helping researchers fine-tune their algorithms over time.
By combining AI with high-throughput phenotyping, researchers can work faster and smarter. Automated trait measurement speeds up plant breeding, improves disease resistance studies, and refines agronomy trials.
AI isn’t here to replace crop scientists; it’s here to empower them. With tools like Hiphen’s technology, researchers can push the boundaries of crop innovation, making smarter, more sustainable decisions for the future of agriculture.
According to Hiphen, “AI has brought revolutionary changes to agriculture, increasing efficiency, precision, and productivity. However, it complements human expertise rather than replacing it.”
AI is transforming plant breeding, particularly in predicting how a genotype will perform in diverse environments. Imagine you're a plant breeder with a promising new hybrid. Before testing it across different soil types, climates, and regions, you need insights on where it will thrive. By training AI models on historical hybrid data—considering past performances under various conditions—researchers can now predict how new hybrids will behave in different environments.6
• Predictive Model Generation: AI-powered models analyze genetic, phenotypic, and environmental data to forecast which plant traits will perform best in specific locations. Breeders benefit from defining ideal crop profiles for a given area: This targeted approach saves time by narrowing down the best progenies to test in that environment.
• Phenotypic prediction to optimize resources: Through AI-driven simulations, researchers can model crop growth in various conditions to understand how plants may adapt to new environments. This accelerates breeding cycles, allowing breeders to make informed decisions with fewer field tests.
Plant breeders traditionally spend years assessing crop performance across different locations. AI expands their decision-making capabilities by providing data-driven insights, reducing risks, and offering deeper segmentation criteria for selection.7
At Doriane, machine learning is used to uncover complex relationships within phenotypic, genetic, and environmental datasets. Our digital platform empowers researchers to predict crop performance and enhance selection accuracy.
In collaboration with RAGT, AI researcher Rony Charles successfully developed a neural network model to predict corn hybrid performance under specific soil, weather, and field conditions.8
He explains: “A notable example is the collaboration with RAGT, where a neural network model was developed to predict the suitability of hybrid corn for specific growing conditions with 95% accuracy. This model helps plant breeders make informed decisions, ensuring that new crop varieties are well-adapted to their environments.”
By leveraging AI, plant breeding becomes faster, more efficient, and better tailored to the challenges of modern agriculture. With AI-assisted predictions, researchers can accelerate innovation, improve crop resilience, and ultimately, cultivate a more sustainable future.9
Read the full report: AI in agriculture research.
The integration of generative AI into the ideation process for crop science research could transform the way scientists develop new processes, design experiments, and explore new agricultural solutions.
We've heard about customers beginning to use generative AI in brainstorming sessions within a multi-disciplined breeding team. The idea is simple: bring a language model like ChatGPT to the table alongside agronomists, data scientists, and biologists, to explore the potential outcomes.
"We started using OpenAI during some trait-brainstorming meetings—more out of curiosity than expectation,” explains an R&D director. “We input trial results, weather patterns, soil profiles, and sensor-derived omics data.”
The result? AI-generated suggestions that sometimes stretch beyond current feasibility, but often reveal unexplored avenues or unexpected trait interactions. While not all proposals are actionable, some have sparked innovative pilot studies that would not have emerged from traditional discussions alone.
In this context, generative AI acts like a tireless colleague—one who draws connections across disciplines and isn’t limited by conventional thinking. It raises questions, suggests alternatives, and helps uncover blind spots.
Beyond brainstorming, generative models have been used to contribute to scientific discussions. For instance, in the ongoing project “One Hundred Important Questions Facing Plant Science”, generative AI was able to generate complementary questions that had not yet been raised by the human panel of experts 10.
Creating effective AI tools for agriculture involves more than just implementing algorithms. Successful integration of AI into agriculture research requires a deep understanding of the domain, access to high-quality datasets, and collaboration between technologists and agricultural experts.
Machine learning tools justify their value on large datasets, and various data types, but they still need to offer intuitive user interfaces that allow researchers to apply them effectively. Data integration across different research areas, such as crop genetics, envirotyping, and agronomy, is critical for the success of AI tools in agricultural research.
Combining phenotypic, genotypic, and environmental data offers a holistic view that enhances decision-making in crop research. This organized data structure is essential for enabling AI.
For AI to deliver its full potential in plant breeding and agronomy testing, effective data management is essential. AI technologies rely on massive datasets, to make predictions and recommendations.
Doriane brings all its expertise to facilitate AI adoption and make AI projects easier for data scientists.
Djampa, a data scientist at Doriane : “Currently 70% of the effort in an AI algorithm development project is done on structuring datasets then choosing models and training them is the fun part of the project” This integration makes AI more effective, providing valuable insights that were previously inaccessible.
One major challenge is change management. Machine learning relies on structured data. Setting up the correct parameters from the start is crucial to ensure valid and useful statistics. This extends the role of data analysts to define and ensure these parameters, rather than relying on a handover between technicians who may not align with the necessary standards. Crop innovation companies typically invest around 20% of their revenue in R&D on average, but, in a market where money is tight, there is less room for delays and waste. Every step must be efficient and precise, especially in a business where it takes 10 years to get a new variety in the market.
Moreover, change management can be particularly challenging in innovation teams. For instance, intuitive plant breeders with historical expertise may resist the data-driven approaches of the new generation of plant breeders. This resistance to change can slow down the adoption of new technologies. Overcoming this requires strong leadership, clear communication about the benefits, and a collaborative approach to integrating new methods with traditional expertise.
At Doriane, we assist clients in adopting machine learning by helping them establish clear data frameworks.
No model can fully replace domain knowledge and intuition. In your job as a crop scientist, AI can help you save time, conserve resources, and make better decisions—but it cannot replace your experience, your creativity, and your understanding of research objectives.
And there's so much to explore with AI: Some data scientists even say that the first level of AI includes tools like calculators or regression analysis. Use cases such as deep learning and machine learning for predictive analysis are already widely adopted by some companies.
We're entering a new chapter—finding meaningful applications for generative AI tools like ChatGPT. The challenge is to identify how these can be applied meaningfully in agriculture innovation.
At Doriane we are exploring such technologies to improve the user experience for breeders and agronomists on our platforms. Machine learning models rely on user feedback to continually learn and improve. While machine learning can provide relevant recommendations, final validation depends on rigorous experimentation by crop scientists, following established statistical standards.
AI isn’t just about making predictions; it's about unlocking the future of agriculture:
Doriane’s expertise in managing and analyzing agronomic data, combined with the use of machine learning and public data repositories, is driving major progress in crop innovation. Learn more on our "Your Project" page
As AI continues to evolve, it has a key role to play in the development of resilient crops that excel in challenging conditions such as saline soils, extreme heat, drought, and biotic stress. This approach supports global food security, promotes biodiversity, reduces dependency on chemical inputs, and helps ensure sustainable farming practices in the face of environmental challenges.
Source:
1. Davison, A. "AI and the Futureof Agriculture." IBM Think Blog, 24 September 2024.
2. Alam, A. "Perspectives onArtificial Intelligence in Agriculture." Current Agriculture ResearchJournal, vol. 12, no. 1, 2024.
3. Rai, K.K. "IntegratingSpeed Breeding with Artificial Intelligence for Developing Climate-SmartCrops." Molecular Biology Reports, vol. 49, 2022, pp. 11385–11402.
4. Ali, Zulfiqar, Asif Muhammad,Nangkyeong Lee, Muhammad Waqar, and Seung Won Lee. 2025. "ArtificialIntelligence for Sustainable Agriculture: A Comprehensive Review of AI-DrivenTechnologies in Crop Production" Sustainability 17, no. 5: 2281.
5. Wageningen University &Research. "Artificial Intelligence." WUR Research Themes, 2025.
6. Authors Unknown."Assessing Environment Types for Maize, Soybean, and Wheat in the UnitedStates." Field Crops Research, vol. 270, 2021, p. 108198.
7. Bose, S., Banerjee, S., Kumar,S., Saha, A., Nandy, D., & Hazra, S. "Review of Applications ofArtificial Intelligence (AI) Methods in Crop Breeding." Journal of PlantGenomics, vol. 12, no. 4, 2023, pp. 567–589.
8. DanielWallach, Pierre Martre, Bo Liu, Senthold Asseng, Frank Ewert, et al.. Multi-model ensembles improve predictions ofcrop-environment-management interactions. Global Change Biology, 2018, 24 (11),pp.5072-5083.
9. Rony, A. "TitleUnknown." HAL Archives, Document ID: hal-02625468.
10. Muhammad Amjad Farooq et al., Artificial intelligence in plant breeding, Trends in Genetics, Volume 40, Issue 10, 2024, Pages 891-908, ISSN 0168-9525.
11. McKinsey & Company. "From Bytes to Bushels: How GenerativeAI Can Shape the Future of Agriculture." McKinsey & Company, 2024.
Did you find this article useful? Share it!
