Crop Monitoring

shutterstock_1162991032.jpg

Low cost and accurate assessment of crop and soil health has long been key to a successful farm and agricultural economy. Recent advancements in drone and satellite technology enable the acquisition of cost effective, timely and localized high resolution multispectral imagery of agricultural land. AI and machine learning offers the ability to recognize highly valuable patterns in this and similar imagery.

Governments often want to understand where soil is degrading and inventory which crops are present (crop identification) in which areas. NGOs and hedge funds often want to predict future yields [1], the former to predict food scarcity, the latter to modify purchases in wheat, corn and other futures. Farmers want to know exactly which crops to spray with fertilizer or pesticide, thus reducing cost and impact to the environment.

At Xyonix we have deep expertise analyzing multispectral imagery and building machine learning and AI models to automatically do things like identify crops and assess crop health.

Does your application gather agriculture related imagery? If so, contact us, and perhaps we can help you glean the insights that will transform your business.

References

1 Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data, Jiaxuan You et al.

2 Machine Learning in Agriculture: A Review, Liakos et al