What if family-owned farms could have access to technology that leads to increased food production at a lower cost and lower environmental impact than current technologies?
We can combine hardware improvements with powerful cloud-based software that will empower US farmers to move from sporadically collected data and information to real-time knowledge that drives productive action.
Our user interviews have identified three critical needs specifically for BEDS.
- Drive Action - Users we interviewed want us to close the gap between images and actions. While multispectral images can provide substantial quantities of useful and unique data, end-user farmers often see these as “pretty pictures with little application to what we do every day.” Actions based on the images are what drives value to these end users.
- Manage the Compute Load - Multispectral image processing is a compute-intensive process. Many US farm operations have surprisingly capable computing resources of their own, but few have the size and scale of computing needed to manage terabytes of image data and process it successfully into recommended actions for their specific operation. Cloud computing offers a way forward but few farming operations can justify the cost of their own private cloud infrastructure nor do they have the technical experience to create their own solutions quickly and maintain them over time.
- Learn Together - While one farm and one farmer may learn over time through personal experience, this learning rate pales in comparison to what a group of farmers can learn from each other when working together. Where the extension services of the past successfully delivered insights and Brilliant Enhanced Diagnostic Software (BEDS) for Crop Diagnostics recommendations based on precise data collection and collaborative research, many farmers we have spoken with to date can see a place for common interpretive tools and crowdsourced solutions.
Farm operations vary significantly in their land size, crop diversity, ability to collect necessary data, and options for managing emerging challenges and crop stressors. Crowdsourced data combined with cloud analytics is key to BEDS’ success. Using multispectral images and supporting data streams from multiple farms and areas, BEDS can learn from the collection and provide tailored action recommendations back to individual operations. BEDS will continue to learn from user feedback on recommendation quality, meaning the system will continuously improve over time and adapt to new information and situations.
Today's high cost of multispectral imaging sensors and limited means to drive this data to productive action recommendations for farmers is blocking US agricultural performance growth.
Our Agricultural Drone project will address these challenges by developing a crop diagnostic action recommendation system using a new low-cost multispectral imaging approach combined with powerful cloud-based machine learning algorithms.
We're working with students at universities around the world on our Agricultural Drone project. Download the file below to learn more.
Our Agricultural Drone project will address these challenges by developing a crop diagnostic action recommendation system using a new low-cost multispectral imaging approach combined with powerful cloud-based machine learning algorithms.
We're working with students at universities around the world on our Agricultural Drone project. Download the file below to learn more.
| ||||||||
Our user interviews have identified three critical needs specifically for BEDS.
- Drive Action - Users we interviewed want us to close the gap between images and actions. While multispectral images can provide substantial quantities of useful and unique data, end-user farmers often see these as “pretty pictures with little application to what we do every day.” Actions based on the images are what drives value to these end users.
- Manage the Compute Load - Multispectral image processing is a compute-intensive process. Many US farm operations have surprisingly capable computing resources of their own, but few have the size and scale of computing needed to manage terabytes of image data and process it successfully into recommended actions for their specific operation. Cloud computing offers a way forward but few farming operations can justify the cost of their own private cloud infrastructure nor do they have the technical experience to create their own solutions quickly and maintain them over time.
- Learn Together - While one farm and one farmer may learn over time through personal experience, this learning rate pales in comparison to what a group of farmers can learn from each other when working together. Where the extension services of the past successfully delivered insights and Brilliant Enhanced Diagnostic Software (BEDS) for Crop Diagnostics recommendations based on precise data collection and collaborative research, many farmers we have spoken with to date can see a place for common interpretive tools and crowdsourced solutions.
Farm operations vary significantly in their land size, crop diversity, ability to collect necessary data, and options for managing emerging challenges and crop stressors. Crowdsourced data combined with cloud analytics is key to BEDS’ success. Using multispectral images and supporting data streams from multiple farms and areas, BEDS can learn from the collection and provide tailored action recommendations back to individual operations. BEDS will continue to learn from user feedback on recommendation quality, meaning the system will continuously improve over time and adapt to new information and situations.
Today's high cost of multispectral imaging sensors and limited means to drive this data to productive action recommendations for farmers is blocking US agricultural performance growth.
Our Agricultural Drone project will address these challenges by developing a crop diagnostic action recommendation system using a new low-cost multispectral imaging approach combined with powerful cloud-based machine learning algorithms.
We're working with students at universities around the world on our Agricultural Drone project. Download the file below to learn more.
Our Agricultural Drone project will address these challenges by developing a crop diagnostic action recommendation system using a new low-cost multispectral imaging approach combined with powerful cloud-based machine learning algorithms.
We're working with students at universities around the world on our Agricultural Drone project. Download the file below to learn more.
| ||||||||
|
We are seeking qualified external investors interested in supporting our agricultural drone project.
Click the button to get in touch with us today! |
|