At present, agriculture faces the constant challenge of control pests that threaten production. The ‘Predicting Crop Pests Using AI’ course allows you to delve into the artificial intelligence applied to the agri-food industry, a growing sector. You’ll learn how to use machine learning y computer vision to create predictive models to improve pest management. You’ll also learn about the integration of IoT sensors and systems in smart greenhouses for a early detection more accurate. Furthermore, it addresses ethics and sustainability in the use of these technologies.
Cross-cutting
AI Academy
3 pm
Predicting Crop Pests Using AI
AI Academy
3 pm
Introduction
Objectives
-
Identify common pests in greenhouses and his economic impact.
-
To recognise environmental factors which encourage their proliferation.
-
Explore traditional techniques and their limitations.
-
Understanding the role of the AI and machine learning in prevention.
-
Analyse AI tools and platforms applied to agriculture.
-
Assess success stories AI-based pest diagnosis and prevention.
-
Integrate sensors and images to improve monitoring in greenhouses.
Table of Contents
TEACHING UNIT 1: PESTS IN PROTECTED AGRICULTURE
1. The most common pests in greenhouse crops
2. Biological cycles and environmental conditions that favour their proliferation
3. The economic and productive impact of pests on intensive horticulture
4. Traditional techniques for pest monitoring and control
5. Limitations of conventional methods in early prediction
TEACHING UNIT 2: ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING IN AGRICULTURE
1. AI, machine learning and deep learning
2. Types of models used in agriculture
3. Current tools and platforms for implementing AI in agricultural settings
4. Successful applications of AI in the diagnosis and prevention of diseases and pests
5. Ethics, sustainability and challenges in the use of AI in agribusiness
TEACHING UNIT 3: DATA COLLECTION AND PROCESSING IN SMART GREENHOUSES
1. Agricultural sensors and IoT systems: types, functions and deployment in greenhouses
2. Critical variables for pest prediction
3. Integration of multispectral, RGB and thermal imagery into monitoring
4. Data storage, labelling and cleaning for model training
5. Data quality and its impact on the predictive accuracy of algorithms
TEACHING UNIT 4. DEVELOPMENT AND TRAINING OF PREDICTIVE MODELS
1. Selection of relevant variables and design of datasets
2. Training, validation and evaluation of predictive models
3. Improvement techniques: hyperparameter tuning, regularisation and model ensemble
4. The use of computer vision to identify pests in images
5. Early detection and automated AI-based warning systems
More related courses
Cross-cutting
Cross-cutting
35 hours
Artificial Intelligence and Intellectual and Industrial Property Rights
View course →Cross-cutting
Cross-cutting