Browsed by
Tag: Predictive analytics

Precision Farming, or Can a Cow be a Sensor?

Precision Farming, or Can a Cow be a Sensor?

riverOver the weekend, I had a chance to read an excellent book called “A River Runs Again”, by Meera Subramanian. Written in the “sandals on the ground” journalistic style, Subramanian uses fluid prose to document her travels across India and her interviews with various people and entities.

However, this is not just another book, listing the environmental and social issues faced by a developing country. The difference in this book, which is divided into sections based on the Five Elements–  air, earth, water, fire, and ether – is the real life stories of positive change being brought about by organizations and individuals – from conversion back to organic farming to creating a vulture aviary to bring back the Parsi Sky Burial ecosystem…

Though not explicitly stated, these change agents are using technology as a growth enabler – which brings us to “smart farming”. There has been quite a bit of work done around ” smart farming” or “precision agriculture“. The Food and Agriculture Organization of the UN (FAO) predicts that the global population will increase to 9.6 billion people by 2050 – and 70% more food needs to be produced to feed that population. Precision agriculture tries to use existing technology like GPS, sensors, big data, IoT and analytics to optimize the crop yields. Even the farm animals play a part, with embedded IoT sensors to reduce the carbon footprint. It does not imply automated farming by machines, but helping the farmer’s gut instinct with intelligent decisioning.

Graphic_Japanese_Farming_v5-01As the author of a report on smart farming states, “I would like to highlight the fact that the aim should not be ‘industrializing’ agriculture, but make agriculture more efficient, sustainable and of high quality. We should not look for revolutions. We should look for re-interpretation of the farming practices through use of data-centric technologies. And this re-interpretation should be placed also within a new vision of rural areas.”

There was another article recently which talks about venture funding for companies using advanced data collection and analytics in agriculture. A good example they give is that of a machine, which can “visually characterize each plant through real-time image capture and processing, use algorithms to determine which portions of the plant to keep and precisely eliminate the portions of the plants that are unwanted.

Their Zea product enables high-throughput, field-based phenotyping. Using computer vision, Zea counts plants, measures plant spacing, builds canopy height distributions and measures key physiological parameters — all based on imagery. In our minds, this is machine learning at its finest…”

The demand is there, and technology is available now. The piece which is missing is to make the technology accessible and affordable for those who need it the most…