Category: Uncategorized

AI x Agriculture
Agriculture is one of the most historical industries. The most traditional agriculture utilizes simple tools like sledge and livestock to increase efficiency, modern agriculture uses more advanced mechanical utilities such as electric tiller and tractor. Although the advanced tools significantly increase productivity, they still lack specification and management and thus causes pollution (ie. fertilizer, pesticide, contamination from livestock, etc.) and waste of energy. However, with AI tools, specifically prediction and agriculture robots, agriculture can achieve detailed management and thus reduce pollution.
Robotics is a broad application field including AI, mechanical engineering, electric engineering, etc. Unlike the fancy robots shown in movies, agriculture robots are more like machines that are informed AI and can finish some tasks. With the help of AI, robots can outperform human in managing and harvesting and significantly reduce human labor work. Managing plants need tremendous inspections and works such as checking pests and soil, but robots not only free human from the redundant work but also are more accurate. For example, R2Weed2 can detect weeds and remove them effectively, and it can also perform soil analysis, which is almost impossible for farmers to achieve for each small region of soil. The analysis results can be further used for other AI program to propose fertilizer or pesticide plan, which optimize environmentally harmful products efficiency and growth of plants.
Other AI tools can also help with agriculture such as machine learning (ML), computer vision (CV), etc. Roughly speaking, ML is a program that is fed with data to train and make prediction about new data, CV is to teach program to see things and do inference as human such as recognizing human faces. Scientists has been trying for decades about training ML to predict crop output in some given conditions like season, soil, etc. This helps farmers to decide what to grow on their land such that the output can be maximized. CV can be used in detection such as detecting pests, crop health, weeds (R2Weed2), etc., which helps farmers to detailly manage each plant. As the output is maximized in each land, fewer lands and resources will be used and wasted.
Despite the benefits of using AI in agriculture, there are some disadvantages such as AI may be less accurate and experienced than human when detecting weeds and pests. However, as AI is growing rapidly nowadays, more accurate algorithms will be proposed and hopefully AI can fully take charge of agriculture and reduce pollution.

CHENHAO ZHANG

AI + Transportation

Traffic pollution contributes to a large part of environment pollution, such as air pollution (greenhouse gas and road dust emission) and noise pollution. In urban aeras, traffic is one of the major sources of air pollution, which significantly affects our life. However, with the unprecedented development of artificial intelligence (AI), transportation is revolutionized, pollution can also be reduced. Signal control, navigation, and autonomous vehicle (AV) are several fields in transportation that are most related to our life and have already been cooperated with AI.
Traditional signal control uses fixed signal plan, which means that the duration and offsets of lights will be constant. Although fixed timing plan is stable and works for the most scenarios, it fails in some scenarios like congestion because it cannot change based on various traffic states. However, as AI can be involved, real-time signal control is possible. Real-time signal control changes light duration and offsets based on current traffic state and thus can be adaptive and flexible to resolve congestion. Google in 2021 launched a project that uses AI in signal control to make traffic lights more efficient. Apart from AI controlled signal that reduces congestion, AI also helps to navigate drivers (ie. Google map navigation) and then reduce congestion in one region. When detecting high traffic volume or density in one region, AI can propose different routine plan for nearby drivers such that traffic flow can be divided and balanced to prevent congestion. Faster traffic flow and less congestion reduces fuel usage and air pollution.
With the deployment of intelligent signal and navigation, the development of AVs can be accelerated. Since AV is controlled by computer, it accelerates and brakes smoother, which makes fuel uses more efficient and reduces energy consumption. Ideally, after all vehicles become AVs, vehicles together with signal and navigation can be fully controlled by AI, efficiency will be optimized, and congestion will be minimized.
With all the benefits of AI being said, the application is still challenging. Unlike classifying an image where making mistake is tolerable, any mistake in real-world application may be fatal, such as turning on the wrong signal light or failing to recognize a pedestrian in AV. Therefore, computer scientists and traffic engineers are still seeking better AI tools to accomplish cleaner and faster traffic.

CHENHAO ZHANG