Please describe your proposed solution.

DigiFarm has successfully completed a Fund 8 funded project titled: "Open ledger for agricultural land" (Idea #18354) where the purpose and objective was to create the POC solution for digitising 914 agricultural field boundaries in Tanzania, where we are working on collaborating on implementing this in the last mile delivery with UNCDF, Gates Foundation and UN, and the benefits from this project and how it helped smallholder farmers included:

1. Benefits included improved access to micro-financing for crop-input, i.e. ~10-12% lower cost
2. Digitisation of field boundaries and measuring of this opens up a new market for carbon credit accessibility, new revenue streams for farmers, i.e. ability to increase revenue per ha of ~40%
3. Ability to have an independent source of field-level data, historically up to 35 years creates a powerful angle for negotiating terms with agricultural lending institutions, credit rating, insurance premiums and crop input suppliers, enabling farmers to take back the control of their own data.

This project builds on the original idea successfully completed in Fund 8 and also presented during the most recent Town Hall (12.07.2023) as the cornerstone of enabling wide-scale adaption (Oracle) of digital identity, open ledger of agricultural field boundaries and blockchain components to create a decentralised, independent source of truth for smallholder farmers in the Cardano ecosystem, hence, this project will be focused on expanding the reach and impact of this pilot project completed in Fund 8 across all the cropland area in Kenya and Tanzania, reaching over 75+ million hectares of farmers.

The current problem in smallholder markets is firstly that 84% of the world’s 570 million farms are smallholdings; that is, farms less than two hectares in size. Many smallholder farmers are some of the poorest people in the world. Tragically, and somewhat paradoxically, they are also those who often go hungry. Lastly, currently 29% of the world's agricultural food production is produced in smallholder market but this is forecasted to change drastically as smallholder farmers gains access to better agronomic advise, crop-input prices and micro-financing.

Additionally, in order to provide additional context on the agricultural market in general:

1. 40% of all agricultural fields are over fertilised
2. Farmers are losing 10-15% on adequate input application (crop protection, seeds and fertiliser)
3. In the most advanced agricultural nation, US, still only 25% use precision ag-services
4. Agricultural fields in Tanzania and Kenya are on avg. smaller than 0.5 ha’s rendering publicly and freely available SatEO insufficient, i.e. this is a largely untapped market

The solution we're building in this project will enable smallholder farmers to easier access financing, agronomic advisory and build their credit profile. Furthermore, with nearly 80% of households in Tanzania engaging in agriculture and at least one third gaining more than half of their income from agricultural activities, while the agriculture sector in Kenya employs more than 40 percent of the total population and 70 percent of the rural population, access to finance for small-scale producers is a major catalyst to broad based economic growth. For a long time and especially in traditional forms of financing, one of the key limiting factors for access to loans for smallholder farmers has been lack of collateral. Looking at land ownership registration for instance, data collected by Tanzania’s bureau of statistics in 2018 shows that out of 8.7 million farms surveyed only 18% were registered.

In addition to this - Small-scale farming systems already grow 50% of our food calories on 30% of the agricultural land. When access to inputs and conditions are equal, smaller farms tend to be more productive per hectare than much larger farms.

The current problem is the lack of historical and in-season data to assess credit risk on smallholder farmers, this due to a lack of infrastructure consisting of agricultural land classification, crop classification, long-term productivity assessment (20-30+ years) on the individual farm-land and field boundaries. Currently, field boundaries are manually created by field agents walking the corners of a physical agricultural field and geo-tagging those boundaries, this is time-consuming, expensive and often inaccurate. In order to provide a reliable and affordable solution the only way is to automate this through the use of deep learning object detection and high-resolution Satellite data.

Please define the positive impact your project will have on the wider Cardano community.

The solution will address the following sections of the challenge:

• National governance systems - New governance systems for nation states
• Climate Change - Solutions that help to solve environmental issues
• Business solutions - Software products, data management, process management, data management solutions (CRM, ERP etc), privacy products**.**
• Artificial intelligence - ability to promote and deliver ecosystem based platform and data layers based on AI and SatEO for broader Cardano users and developers can build on top of.

Furthermore, the solution will enable smallholder farmers to easier access financing, agronomic advisory and build their credit profile. Furthermore, with nearly 80% of households in the region engaging in agriculture and at least one third gaining more than half of their income from agricultural activities, access to finance for small-scale producers is a major catalyst to broad based economic growth.

For a long time and especially in traditional forms of financing, one of the key limiting factors for access to loans for smallholder farmers has been lack of collateral. Looking at land ownership registration for instance, data collected by Tanzania’s bureau of statistics in 2018 shows that out of 8.7 million farms surveyed only 18% were registered. In addition to this it is a known fact that still 30% of the world's agricultural fields are not mapped nor digitised which also creates risk in terms of property ownership and rights.

The current problem is the lack of historical and in-season data to assess credit risk on smallholder farmers, this due to a lack of infrastructure consisting of agricultural land classification, crop classification, long-term productivity assessment (20-30+ years) on the individual farm-land and field boundaries.

Currently, field boundaries are manually created by field agents walking the corners of a physical agricultural field and geo-tagging those boundaries, this is time-consuming, expensive and often inaccurate. In order to provide a reliable and affordable solution the only way is to automate this through the use of deep learning object detection and high-resolution Satellite data.

What is your capability to deliver your project with high levels of trust and accountability? How do you intend to validate if your approach is feasible?

DigiFarm has successfully demonstrated it's internal capacity to successfully achieve KPIs in the project funded in Fund 8 "Open ledger for agricultural land" (Idea #18354) and was highlighted recently selected as one of the projects spotlighted amongst the recently completed 500 Catalyst projects and presented during the Town Hall (12.07.2023).

Additionally, DigiFarm’s team is the ideal fit for the project as our core team has extensive experience in (a) developing agricultural technology for crop-monitoring using AI and remote sensing (Satellite data) to the agribusinesses market (B2B/B2G) using SaaS-models. Successfully built commercial agricultural technological solutions using remote sensing (Satellite-data) and AI across 100 million hectares: >90% accuracy in crop Detection and >85% accuracy in yield-prediction in soybean and corn (US/Brazil) (b) core team has over 15+ years of on-the-ground crop-producing (farming) experience and close partnership withs Felleskjøpet (largest ag-coop in Norway, NLR (Norwegian Agricultural Advisory Organisation) and University of Life Sciences (NMBU) (c) commercial and corporate Ag-market: over 20+ years combined corporate agriculture leadership experience (d) over 40+ experience in agronomy academic research internationally.

Additional qualifications in DigiFarm’s core team and founders (10) include technical and agronomical experience: (a) over 40 years combined international work experience in precision-Ag projects in Canada, USA, Germany, Switzerland, Brazil, Australia, Russia and Ukraine (b) successfully filed 5 patents (AI-based technologies) in agriculture/biology (e) developed technology for Zoner.ag (one of first geospatial web-platforms for analyzing agricultural fields) successfully acquired by Bayer to become the geospatial engine of Xarvio digital-farming platform (owned by BASF). Management capacity: led and managed the Bayer CropScience division as Global Technology Lead with the Digital Farming Division, overseeing expansion Xarvio to over 100 employees, serving over 3.4 million farmers and agronomists worldwide (b) founded and grew AI-based Gamaya (Swiss-based) agtech startup, managed team growth to 45 employees in under 24 months and secured $20 million in VC funding from Mahindra.

Lastly, we will also include third party partner to help implement the DID prototype part of the project: https://www.proofspace.id/.

What are the key milestones you need to achieve in order to complete your project successfully?

The first milestone during this project will be during the M1-M4 period and include:

1. All SatEO imagery data at 1 meter pixel resolution processed across the entire country-wide scale of Tanzania and Kenya for 2023/2024 season successfully (68m hectares) including creation of mosaic base-map available in open web-app for end-users and Cardano environment.
2. Successful collection of training data (labelling manually field boundaries in both countries for training and validation data for the deep neural network model), which would include approx. 250,000 boundaries in total (0.4% of every crop land area).

The acceptance criteria will be the accuracy of the output, i.e. 0.90 and above as well as the successful completion and creation of a fully working web-application with this data displayed and prototype open to all stakeholders.

>The second milestone during this project will be during the M4-M7 period and include:

1. Successfully developed model for automatically delineated field boundaries in Kenya and Tanzania at 1 meter per pixel and the KPI of this milestone will be to achieve higher than 0.90 IoU accuracy in the output (i.e. 90%) across the entire 68 million hectares of crop land area in both countries. This process will include significant model training and be compute intensive (GPU/HPC) which is why we have included 3 months for this stage.
2. Successfully post-processed all field boundaries with deep-resolution S2 imagery at 1 meter and loaded in our AWS cloud environment and subsequently in the web-application.

The acceptance criteria will be the accuracy of the output, i.e. 0.90 and above as well as the successful completion and creation of a fully working web-application with this data displayed and prototype open to all stakeholders.

>The third milestone during this project will be during the M7-M10 period and include:

1. Successfully process and run historical vegetation data (productivity/yield) across all automatically delineated field boundaries for the entire 35 year period available (Landsat/30m), which will show which fields are performing well over time and which ones are not.
2. Successfully embedded this data into the web-application for consumption by stakeholders.

The acceptance criteria is to be able to run this index across 90% of all the automatically delineated field boundaries, this not being 100% is due to some filtering out of boundaries due to size of boundaries, lack of cloud-free dates from Sentinel-2 and lack of data consistency on Landsat as examples.

>The fourth milestone during this project will be during the M10-M12 period and include:

1. Successfully established partnerships in the agricultural value chain in Kenya and Tanzania, including third party partners both from the private sector such as Agribora, Safaricom, Kenyan Livestock Association, IM Bank as well as in the NGO sector including: Gates Foundation, UNCDF and World Bank
2. Successfully implemented and put farm and field level data on blockchain and accessible to smallholder farmers, including 50,000 farmers actively using platform within first 12 months.

The validation criteria will include 3 secured partnership in private or NGO sector to leverage and reach smallholder farmers through channel networks as well as independently 50,000 MoA users on the open data. The end goal in this project is to be able to leverage the Cardano community to extend the benefits and value-add that the ecosystem can bring to these farmers through aux services.

>The final milestone will be successful completion of all milestones described in previous section from M1 to M4 and the true validation will be the benefits it brings smallholder farmers directly in Kenya and Tanzania as well as to the ecosystem surrounding these farmers, we have estimations and KPIs including:

1. Ability to reduce financing costs by 5-10% due to presenting historical and independent data to financial lending in agricultural value chain, i.e. farmer should be able to get lower interest rates and better terms due to presenting historical and reliable crop production data to reduce risk on bank's side and increase upside and automation of underwriting loans, i.e. also creating more lending options for smallholder farmers in need.
2. Ability to reduce insurance premiums and claim inefficiencies by 10% - similar to what described above the ability to present historical data on crop production showing stability and "lowering" the risk for the insurance company and issuer for "claim" or yield loss with farmers will help lower premiums for the farmer.
3. Lastly, the ability for farmers to access VRT technologies through the platform is a longer term goal which will extend after this project, but this will enable farmers to reduce their crop input cost by using automatically delineated productivity zones (based SatEO and vegetation data) to apply optimal quantity of fertiliser, seed and fungicide, this can reduce crop input cost by up to 15% and increase yield by up to 10% but this approach requires extensive local partner input and support, i.e. this will be done in continuation of this project.

Who is in the project team and what are their roles?

DigiFarm’s team is the ideal fit for the project as our core team has extensive experience in (a) developing agricultural technology for crop-monitoring using AI and remote sensing (Satellite data) to the agribusinesses market (B2B/B2G) using SaaS-models. Successfully built commercial agricultural technological solutions using remote sensing (Satellite-data) and AI across 100 million hectares: >90% accuracy in crop Detection and >85% accuracy in yield-prediction in soybean and corn (US/Brazil) (b) core team has over 15+ years of on-the-ground crop-producing (farming) experience and close partnership withs Felleskjøpet (largest ag-coop in Norway, NLR (Norwegian Agricultural Advisory Organisation) and University of Life Sciences (NMBU) (c) commercial and corporate Ag-market: over 20+ years combined corporate agriculture leadership experience (d) over 40+ experience in agronomy academic research internationally.

Additional qualifications in DigiFarm’s core team and founders (10) include technical and agronomical experience: (a) over 40 years combined international work experience in precision-Ag projects in Canada, USA, Germany, Switzerland, Brazil, Australia, Russia and Ukraine (b) successfully filed 5 patents (AI-based technologies) in agriculture/biology (e) developed technology for Zoner.ag (one of first geospatial web-platforms for analyzing agricultural fields) successfully acquired by Bayer to become the geospatial engine of Xarvio digital-farming platform (owned by BASF). Management capacity: led and managed the Bayer CropScience division as Global Technology Lead with the Digital Farming Division, overseeing expansion Xarvio to over 100 employees, serving over 3.4 million farmers and agronomists worldwide (b) founded and grew AI-based Gamaya (Swiss-based) agtech startup, managed team growth to 45 employees in under 24 months and secured $20 million in VC funding from Mahindra.

• Nils Helset, 15th generation farmer in Norway. Extensive experience with precision agriculture services and agronomy - over 8 years experience in crop-producing, managing over 40k decares of pilot farmers with Felleskjøpet. Linkedin profile: https://www.linkedin.com/in/nilshelset/
• Konstantin Varik - built advanced AI models in agriculture using remote sensing for over 8 years including AI model for crop-yield prediction for maize and soybeans for USA, Brazil and Argentina with 98-99% yield-prediction accuracy 1-1.5 months prior to harvesting (data provided to the USDA). Linkedin profile: https://www.linkedin.com/in/varik/
• Alex Melnichouck founded B2B ag-tech startups Zoner.ag in 2012 (acquired by BASF in 2015), led and managed the global BASF digital farming team for over 4 years. Linkedin profile: https://www.linkedin.com/in/alex-melnitchouck-8977a522/
• Yosef Akhtman founded and grew Gamaya, Swiss-based ag-tech startup focused on remote sensing and AI funded by Mahindra. Yosef is a scientist and inventor with over 5 registered patents in agriculture and biology. Linkedin profile: https://www.linkedin.com/in/akhtman

It is also important to mention here that DigiFarm is a fully independent Norwegian organisation, we have not raised any VC capital and are fully bootstrapped since 2019, this approach and independence makes us an ideal fit for this project.

Please provide a cost breakdown of the proposed work and resources.

The project timeline is estimated to be 10 months, which will enable us to capture and build the models during the growing season in Kenya and Tanzania. The total crop land area to be delineated and analysed is 28 million hectares in Kenya and 40 million in hectares in Tanzania, total of 68 million hectares. The project is ambitious and comprehensive and uniquely innovative as this has not been done previously, both processing entire nations with 1 meter per pixel resolution Satellite imagery (Sentinel-2) but also for automatically delineating boundaries and historical productivity (biomass/yield) over a 35 year period, this project will open up significant opportunities for the eco-system to build services on the dataset.

The external services we will leverage includes:

1. AWS cloud environment for the processing of Sentinel-2 L2A/L1C data
2. Lambda Lab GPU Cloud for training the deep neural network models across high-performance GPUs (A100s)
3. Github/Tensorflow in addition to other software/PM tools
4. We will also be leveraging third party services for putting the data on blockchain, we already have existing partnerships in the Cardano ecosystem to support this

Hosting for the project website and code repositories are provided free of charge via Github. Community outreach will be done via (free) Linkedin, Facebook and YouTube accounts along with Project Catalyst communication channels.

Detailed roadmap above for descriptions of the tasks and work products that will be delivered in three, four-week sprints

• Month 1-4: 200 hours x $65 (175 ADA) = $13,000 and 35,000 ADA
• Month 4-7: 150 hours x $65 (175 ADA) = $9,750 and 26,250 ADA
• Month 7-10: 100 hours x $65 (175 ADA) = $6,500 and 17,500 ADA
• Month 10-12: 50 hours x $65 (175 ADA) = $3,250 and 8,750 ADA
• Professional fees: including legal, accounting, and communications: $4,000 and 8,925 ADA
• TOTAL: $36,500 and 96,425 ADA

How does the cost of the project represent value for money for the Cardano ecosystem?

What we're developing in this project is an "enabler" or a baseline of fundamental data that the ecosystem can build further upon as a community, this is an important component of the vision as digital field boundaries, historical productivity data in a fully independent and unique format (block-chain) represents significant value not only for the Cardano ecosystem as a positive influence on sustainability, digitisation and "oracle" in agricultural farming market as well as this project will directly affect the lives of smallholder farmers in both Kenya and Tanzania, opening up a dataset to entire 68 million crop land to create opportunities, this has not been done before due to several bottlenecks such as:

1. Availability of high resolution Satellite data: DigiFarm's deeply resolved Sentinel-2 at 1 meter represents a unique technology ideally suited for the region, seeing as the high resolution is needed to be able to derive analytics for the boundaries which are typically very small, i.e. 0.5 hectares and below, the alternative to using our data would be to have to buy commercial grade SatEO and the closest resolution wise would be having to buy Airbus Pleaidas data at 50cm which costs €8 per sq.km, considering both countries include a total land area of 680,000 sq.km and we'd require 3-dates the total cost would be €16,320,000 just for the input data to deliver and provide these data layers in the region.
2. Additionally, seeing as DigiFarm leverages open source and publicly available data from Sentinel-2 and then run our deep-resolution on it from 10m to 1m this is ideal to be able to keep promoting the open source and independent use of data to support the ecosystem.
3. Lastly, if we could reach 50,000 farmers which is the goal at the end of this project (and to extend this to 500k the following 18 months) and save 10% on crop input and lower insurance/financing cost by 10%, this is a critical and high potential project.