Easy and cost-effective availability of satellite datasets have ushered in a new era of ‘precision agriculture’. Satellite images ranging from 22cm to a few metres in resolution are processed using Artificial Intelligence (AI), Machine Learning (ML), and Computer Vision (CV) algorithms.
These turn-key analytics enable quantification of biomass or nutrient content, and monitor fields with no bias, free of ground measurement. Combined with agro-meteorological models and established plant health indices such as NDVI, they can be accurately turned into prescriptions to dose fertilisers, water, growth regulators and pesticides. Not only does this reduce the quantity of input required and therefore the cost, it also rationalises inputs and is therefore more environmentally friendly. The resulting output can be used by stakeholders across the value chain to quantify and analyse productivity, plan capex-intensive infrastructure such as irrigation, and also monitor and predict yields.
What’s more, this technology can also play a key role in risk management. Early detection of pest and disease outbreaks allows for rapid action to prevent crop damage and yield loss. Insurance companies globally are also turning to this technology not only to help them monitor/assess risk and determine product pricing, but also to assess damage post adverse events such as cyclones or droughts.