Newswise — Artificial intelligence (AI) and data science are two closely related yet distinct fields that are driving research and innovation in the agricultural and life sciences, among many other fields. The pace of technological advancement in these areas, and the sheer amount of jargon that goes with it, can be overwhelming. To help get you up to speed, here are 10 things to know about AI and data science in general and, more specifically, their influence on the agricultural and life sciences — at CALS and beyond.
**1\. AI focuses on creating systems and software capable of performing tasks that typically require human intelligence.** These tasks include learning from data, recognizing patterns, understanding natural language, solving problems, and making decisions autonomously
**2\. Data science involves extracting meaningful insights and knowledge from data through statistical analysis, machine learning, and data visualization.** It encompasses the collection, processing, and interpretation of large datasets to inform decision-making and uncover trends. Data science provides the foundation for AI by offering the data and insights necessary for training AI models.
**3\. While AI focuses on automating tasks and making intelligent decisions, data science emphasizes understanding data and extracting actionable insights.** A car’s cruise control system illustrates the difference between data science and AI. Traditional cruise control is like data science in that it collects a lot of data from your car to adjust and display your speed. The newer adaptive cruise control, however, is like AI in that it uses real-time data from sensors to adjust a car’s speed autonomously. The system learns from historical data to predict optimal speeds and maintain safe distances between vehicles.
**4\. AI can be categorized into different types based on capabilities.** Narrow AI (or weak AI) is designed for specific tasks — think of a virtual assistant like Siri or Alexa. General AI (or strong AI) aims to emulate human intelligence across a broad range of activities, though it remains largely theoretical. Superintelligent AI surpasses human intelligence, but it’s mostly explored in theoretical research and speculative fiction.
**5\. Generative AI is one of the most familiar forms of artificial intelligence.** Generative AI, which includes well-known software such as ChatGPT and Google’s Gemini, focuses on creating new content from learned data. It can produce text, images, music, and even videos that are often indistinguishable from human-created content.
**6\. Another important type of AI, convolutional neural networks (CNNs), are deep learning algorithms specifically designed for processing and analyzing visual data**. They are crucial in computer vision tasks, such as image and video recognition, object detection, and image segmentation. CNNs involve many-layered neural networks that learn and represent complex data patterns through supervised learning on labeled datasets. They automatically detect spatial hierarchies of features, from low-level edges and textures to high-level shapes and objects.
**7\. AI’s transformative impact extends to agriculture, where it enables more efficient, productive, and sustainable farming practices.** Common AI applications in agriculture include precision farming, which uses AI-driven data analytics to optimize planting, fertilizing, and harvesting and to tailor these processes to specific crop and soil conditions. Computer vision and machine learning techniques are employed in crop monitoring and yield prediction, where they analyze drone and satellite images to assess plant health, detect pests, and estimate crop output. AI-powered robots and automation systems handle tasks such as weeding, harvesting, and sorting crops to improve labor efficiency and reduce waste. Predictive analytics in AI leverage historical data and weather forecasts to help farmers make data-driven decisions about irrigation, crop rotation, and disease prevention that minimize risks and maximize yield.
**8\. CALS researchers are pursuing cutting- edge work at the nexus of AI and agriculture.** For example, a team led by animal and dairy sciences associate professor [Joao Dorea](https://andysci.wisc.edu/directory/joao-ricardo-reboucas-dorea/) is creating AI systems with standard cameras to transform animal health monitoring by enabling real-time assessments of livestock. Advanced computer vision algorithms analyze video feeds to detect subtle changes in animal behavior, posture, and body condition. For instance, AI systems can identify lameness by analyzing walking patterns or spot early signs of illness through changes in eating or social behaviors.
**9\. In the life sciences, AI is driving breakthroughs in research and health care by analyzing complex biological data to accelerate discoveries.** Machine learning algorithms identify patterns in genetic data to aid in the discovery of new drugs and personalized medicine. Deep learning models analyze medical images with unprecedented accuracy, improving diagnostics and early detection of diseases such as cancer and neurological disorders.
AI also facilitates bioinformatics, where it helps decode the vast information embedded in biological sequences to further our understanding of protein structures and better predict gene functions. In drug discovery, AI models predict how different molecules will interact with targets in the body, significantly speeding up the process of finding new treatments. Additionally, AI-powered robotic systems assist in automating laboratory experiments, which enhances precision and throughput in research activities.
**10\. CALS scientists are leading the way with numerous projects that could transform research and health care through AI.** One example: A group of researchers under the direction of biochemistry assistant professor [Duo Xu](https://biochem.wisc.edu/people/xu-duo/) is combining basic life science in biochemistry and structural biology with new AI tools. They’ve employed AI predictive technologies for protein engineering and immunology that can anticipate future viruses. They’re also using AI-driven models to analyze vast datasets of viral proteins and antibody structures to design broad-spectrum inhibitors capable of neutralizing emerging pathogens. By enhancing our understanding of antibody immunity and outsmarting future viruses, CALS researchers are moving toward new vaccines and treatments for preventing future pandemics.
Get Familiar with AI and Data Science
-------------------------------------
Understanding AI vocabulary is essential for navigating the field. This short glossary includes some of the most commonly used terms, from general to more specific.
**Artificial intelligence (AI)**
The simulation of human intelligence in machines designed to think and act like humans, performing tasks such as learning, reasoning, and problem solving.
**Machine learning (ML)**
A subset of AI that focuses on the development of algorithms that allow computers to learn from and make decisions based on data.
**Deep learning**
A subset of machine learning with many-layered neural networks (hence, “deep”) that can recognize complex patterns in large amounts of data.
**Reinforcement learning**
A type of machine learning where an agent (the software in training) learns to make decisions by taking actions in an environment to maximize some notion of cumulative reward.
**Supervised learning**
A type of machine learning where the model is trained on a labeled dataset, meaning that each training example is paired with an output label.
**Unsupervised learning**
A type of machine learning where the model is trained on data that does not have labeled responses, and the system tries to discover the underlying patterns and structure from the input data.
**Neural network**
A series of algorithms that attempt to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates.
**Convolutional neural network (CNN)**A type of deep learning neural network primarily used for analyzing visual data, such as images and videos, by automatically learning spatial hierarchies
of features.
**Computer vision**
A field of AI that enables computers to interpret and make decisions based on visual data from the world, such as images and videos.