GeoAI-Driven Crop Yield Prediction
Current Practices
Manually Counting Wheat Heads to Predict Wheat Yield
Problem Statement: Early, accurate estimation of crop yield can help farmers to plan harvest management, storage requirements, capital management, delivery estimates, and crop insurance assessments. However, crop yield prediction is extremely challenging. For farmers and growers, wheat yield estimation is often performed by randomly selecting and manually counting the number of harvestable heads from a specific length (e.g., 3 or 5 ft) of plant row in various locations around a field. By counting kernels on heads, determining the distance between rows and applying each measure to a formula, an approximate yield can be calculated. This method often has higher accuracy and lower cost than the crop yield prediction model, but is significantly time-consuming and unreliable due to subjective assessments.
Crop yield prediction is an essential metric for making informed management and financial decisions.
Super GeoAI Crop Yield mobile App (Demo)
(1). The following demo uses our mobile app prototype to take photos of wheat heads (about two rows and 3 feet length per photo). The app immediately calculates the crop yield in each photo and the average crop yield in the whole field. Click Here to download the original high-resolution video. You can select the Settings Gear Icon on the lower right-hand side of the player and Select the Quality drop down box that pops up to change YouTube Video Quality Setting.
(2). The following demo uses the smartphone camera to take several photos per representative location around a field and uses our mobile app prototype to calculate crop yield in these photos at one time. Click Here to download the original high-resolution video. You can select the Settings Gear Icon on the lower right-hand side of the player and Select the Quality drop down box that pops up to change YouTube Video Quality Setting.