X Labs of Alphabet, the parent company of Google, has come up with a robotic buggy that travels over crops, and collects data on each individual plant to help gather information on how it interacts with the environment and what can be done to better its nutrient value.
The X Lab team is engaged in developing tools for computational agriculture where new types of hardware softener and sensors will collect and analyze information about the complex world of plants and in the process help in better agriculture production.
The tools are developed under a project named Mineral as the team believes they are the lifeblood of both plants and animals. Minerals are not produced by the human body and it is the consumption of plants that fulfills our need for these elements.
Mineral is still very much in the experimental phase. It was born when the team saw sustainable food production was the need of the need of the hour and the need for digital technology to fill the gaps.
“These new streams of data are either overwhelming or don’t measure up to the complexity of agriculture, so they defer back to things like tradition, instinct or habit,” writes Mineral head Elliott Grant. What’s needed is something both more comprehensive and more accessible.
The whole effort was driven by the need to know if every single plant could be monitored and given exactly the nutrition it needed? If the genetic and environmental drivers of crop yield could be determined? If a crop variety could be matched to a parcel of land for optimum sustainability?
The way to do this, according to the Mineral team was through the “Plant buggy,” a machine that can intelligently and indefatigably navigate fields and do those tedious and repetitive inspections. With such intensive data available on every plant, growers can initiate solutions at that scale as well — how much fertilizer to what insecticide and at a measurable quantity so as no to overuse.
Overuse of fertilizers and chemicals also negatively affects soil health, creating a vicious cycle that makes our farmlands less productive and food less nutritious.
The aim of the project is to help build a more sustainable, resilient, and productive food system.
A change in the way we produce food is urgently needed as rampant use of fertilizers is depleting the earth’s capacity. To feed the planet’s growing population, global agriculture will need to produce more food in the next 50 years than in the previous 10,000–and at a time when climate change is affecting our production patterns.
Of the 30,000 edible plant species that are known, less than 1% are cultivated for human food. Modern agriculture practices focus on cultivating a few crops known to have high yields—today, rice, wheat, and maize provide nearly half the world’s plant-derived calories, according to a United Nations report. Depending on just a few varieties makes us vulnerable to nature’s vagaries and pests.
“From soybean farmers in Argentina to kiwifruit breeders in New Zealand, we heard from breeders that they need to gather much more information on many more varieties of biodiverse plants—and quickly, if they are going find varieties that are resilient and productive in the face of climate change.”
The Mineral team saw an opportunity to build new tools to help breeders and growers embrace the complexities of growing food.
The answer was developing the plant buggy that trundles through various crops gathering data. By combining the imagery gathered by the plant buggy with other data sets like satellite imagery, weather data, and soil information, the team can create a full picture of what’s happening in the field and use machine learning to identify patterns and useful insights into how plants grow to interact with the environment.
The buggy is still at an experimental stage and when it will reach the market and be widely accepted is not known yet.
The buggy comes in various sizes and operates with a solar panel. It has sophisticated cameras and sensors fitted in to collect all kinds of data.
The post Alphabet’s X Lab Develops Robotic buggy that collects Deep Data of individual plants appeared first on Industry Leaders Magazine.