How might we develop holistic solutions incorporating a range of technologies not only to assess and manage the impact of internal and external factors on crop and plant health, but also to develop models that can predict likely impacts and inform actions to prevent and mitigate such damage?
Background/Context
In 2021 the Food & Agriculture Organization of the United Nations (FAO) estimated up to 40 per cent of global crop production is lost to pests each year. Plant diseases cost the global economy over US$220 billion, and invasive insects at least US $70 billion each year. Not only does this cause massive loss of income to farmers it is tragic when FAO estimates hunger affected between 700-829m people in 2021. As climate change is predicted to increase the impact of pests, the losses are likely to increase.
Decades of mono cropping and inappropriate application of fertilisers has impacted soil health, further exacerbated by water challenges. We need a better understanding of conditions to manage crop growth.
Many crops and plants are very sensitive to a range of internal and external factors that can cause them to perish very quickly. Soil parameters impact plant health directly and regular monitoring is paramount to alleviate possible problems.
Plant health management is currently based on human visual reporting and subsequent management. Human errors in timing and / or interpretation impact the timely detection of such issues. Experts in plant health issues cannot be present across all sites. Problems need to be centralised where identification, analysis, and resolution is possible with the best resources and capabilities. Further, past data and causal relationships can inform and support future actions , both pre-emptively and reactively to new incidents.
Advances in automated data collection and analysis, machine learning and the development of artificial intelligence and predictive solutions have improved efficiencies in operations across many industries. The same is possible and increasingly necessary in agriculture to prevent crop and plant losses to enable us to better feed the world.
DS Group is a major conglomerate with multiple locations across India growing crops including macadamia, blueberry, almonds and Stevia and currently expanding internationally.
Objective
Utilise machine learning and AI with hardware to better understand soil and plant parameters to significantly reduce pre-harvest plant and crop losses caused by pests and disease.
Solutions
The desired solution should fulfil the following requirements:
- Allow for multiple crops, plants and other flora to be added and automatic analyses generated.
- Solutions should be capable of application globally.
- Solutions should provide real-time analytics.
- AI algorithms must be capable of identifying plant health issues, interpreting detailed soil and water parameters (surface and deep subsoil).
- Any system should be capable of basic image recognition, voice recognition, and OCR.
- Computer vision algorithms must take inputs from multiple device types – CCTV cameras, drone cameras, shoulder-mounted cameras, handheld mobile device photos and videos. Video formats of all types must be acceptable as inputs to the solution. SONAR or similar inputs will be necessary for deep sub-soil water levels and volumes.
- Systems should be standalone units which can be deployed at remote farm sites with little or no infrastructure and be weatherproof to withstand extreme climatic swings and salinity or humidity.
Reward
- Successful entrants will conduct a pilot project with DS Group spanning 6-12 months to validate the solution and enter into a commercial deployment after incorporating all the learnings from the pilot phase.
- The pilot project will be supported by a SGD20,000 grant from Enterprise Singapore and close guidance from the DS Group team.
Resources
- Data is being collected on a daily, weekly, monthly and seasonal basis. Existing data will be provided on request.
- Teams will be permitted to visit and take data in the form of photos and videos of plants and crops to train machine learning and deep learning models.
How might we develop an integrated low-cost technology solution to protect high-value assets from theft and fire in remote locations?
Background/Context
In 2006, the DS Group revived the endangered forest species, sandalwood, in Madhya Pradesh and established the largest sandalwood plantation as an agro-forestry model in India. Sandalwood takes an average of 18 to 25 years to reach harvestable age. Thus, there is a substantial investment in planting and managing the trees until harvest.
Over that time, the plantations are exposed to risks from nature, especially fire, and theft by individuals and organised gangs. Risk management of these plantations is ineffective given their location and size. Furthermore, being in rural areas implies limited power and connectivity options, which presents additional challenges for technology solutions. The solutions themselves can also be subject to the same risks as the assets they seek to protect.
Certain weather conditions and patterns can be indicative or predictive of fire. Likewise, what human activities might be tracked and assessed to provide insights into possible theft? Many industries monitor and track high-value assets through a range of technologies and adoption of hardware from asset tags through to remote satellite monitoring via satellite.
Objective
DS Group wants to design a web-based platform and low-cost hardware system to provide real-time alerts on intrusion attempts, perimeter infringements, blacklisted entrants and fire outbreaks for remote high-value assets.
Solutions
The desired solution should incorporate the following features:
- Wired solutions with large-sized sensors visible or detectable by thieves are best avoided.
- Longevity of components, power packs, weather proofing and low power usage should be incumbent in any expected solution.
- Real-time alerts on intrusion attempts, perimeter infringements, blacklisted entrants, and/or fire outbreaks.
- The solution needs to be tamper-proof.
- Solar-power supply is paramount to allow stand-alone deployment in remote areas.
- The solution should be low cost and fit for purpose.
Additional Information
- A non-SaaS model is preferred, with servers on premises and ownership of software and source code.
- A hybrid solution of technologies is preferred.
Reward
- Successful company will conduct a pilot project with DS Group spanning 6 to 12 months to validate the solution and enter into a commercial deployment after incorporating all the learnings from the pilot phase.
- The pilot project will be supported by a SGD20,000 grant from Enterprise Singapore and close guidance from the DS Group team.
