Autonomous farming systems use networked cameras and sensors together with machine learning algorithm to constantly monitor an indoor farm’s environment adjust lighting, temperature, humidity, water, and soil nutrient levels to maximize a farm’s productivity. The algorithm also monitor plants and determines if a particular plant is at risk of becoming sick. The system analyzes data and predicts problems that could arise to prompt farmers to take preventative action. It constantly learns from historical data and refines its predictions.
Deep-learning image-analysis software analyzes satellite photos of farmland to forecast crop yields. The software can produce estimates of crop production on a weekly basis by comparing daily photographs of 3 million square kilometers of corn farms with less than a one percent margin of error, allowing farmers, insurers, commodities traders, and governments to make more informed decisions.
A robotic system powered by TensorFlow, Google’s open-source machine-learning software, automatically sorts cucumbers based on their visual differences such as size and shape. The system’s computer-vision algorithms recognize nine different categories of cucumbers. It can sort cucumbers on a conveyer belt with 70 percent accuracy and can do so substantially faster than manual sorting.