What most inspired us to carry out this project is the extreme need to revolutionize the production of small farmers (which in Brazil alone today account for more than 50% of the activity), helping with sustainable, resilient and committed to the environment. environment. According to the UN, they are responsible for producing 80% of the food on the planet. By empowering this small producer, we democratize access to technology and knowledge, maximizing its productivity, enabling its implantation in sustainable agricultural systems such as agro-forestry, biological, pemaculture and others. As there are means that provide greater security and predictability, and even economic gain for the smallholder business, it will be easier for the adoption of agricultural systems that are less intensive and more in harmony with the environment. And through automation, it is possible to help manage and make crops more economical and healthier.
Variation of the total percentage of planted areas in relation to the year and crop
Annual Variation Studies
The system consists of 4 parts:
1 - A modular autonomous mobile robot where the owner can add different modules for different crops, being completely flexible and adaptable to any type of agricultural land with features that enable:
2 – Station for irrigation control consisting of an electric pump drive to supply water to the irrigators (depending on the culture, the type of irrigators is changed, for example: sprinkling, dripping, water cannons, etc.). Components of the irrigation station to improve meteorological control and monitoring:
3 - Solar capture system kit with wifi communication with the irrigation station and the robot, allows the robot to be loaded, the irrigation station to work, to supply the rural property and if it exceeds the return energy use for the governmental distributor's electrical system.
4- Intuitive and easy-to-use mobile and desktop application, with no prior knowledge required for its use, it aims to present all data from NASA satellites, robot and irrigation station (weather) and through the use of artificial intelligence and science of the data it is able to indicate to the producer the amount of fertilizer, ideal level of irrigation, appropriate cultural treatments so that it maximizes the production and productivity of the area, reducing the waste, expenses of inputs and improves the quality and food security of its products.
MUST SEE
See how this will work here and here -> www.safos.us
App prototype video: link
Legend of first link:
1 - Mobile robot with sensors and WIFI, bluetooth and RF connection
2 - Stationary automation system for control of irrigation, pumps and weather station
3 - Solar capture system
4- App intuitive and-easy-to-use.
SDG 1: (1.5 and 1.a)
Through the use of the solution, we democratize the data, reducing the difference in knowledge between a large producer and a small producer, thereby giving a real chance for a small producer to escape poverty.
SDG 2: (2.1, 2.2, 2.3, 2.4, 2.5)
With the efficient use of data, and the decision-making system, it is possible to increase productivity particularly among women, indigenous peoples and family farms, with secure access to productive resources, inputs and knowledge, guaranteeing sustainable food production systems, implementing robust agricultural practices that help maintain the ecosystem, strengthening the capacity for climate change, extreme weather conditions, droughts, floods and other disasters, progressively improving the quality of land and soil.
SDG 3: (3.9)
With a focus on properties of up to 10 hectares that represent 51% only in Brazil, where most farmers use low use of pesticides, we improve the health and well-being of the population and guarantee safer food
SDG 4: (4.7)
Through collaborative and creative education, we have managed to improve the educational quality of the agricultural population, teaching them intuitive programming languages
and assembling modules for each crop they intend to cultivate. These skills will enable mainly young people to promote sustainable development through technology and accessible knowledge.
SDG 5: (5.5 and 5.b)
Possibility of gender equality since anyone can use, assemble and program with our solution, with no distinction of any kind. Promoting the increased use of information and communication technologies.
SDG 6: (6.3, 6.4, 6.5, 6.6)
Through the intelligent control of irrigation we managed to reduce 40% of water expenditure because through our sensors we were able to calculate the evapotranspiration of the plant by crossing with climatic data we can say and activate the irrigation at the optimum point of need of the crop.
SDG 7: (7.1 and 7.2)
With the use of our solar panels and our solar power generation plant, the use of clean energy is fully applicable in our solution, because in addition to feeding the robot, it can feed the property, the irrigation system and even return the network generating credits with the energy company.
SDG 8: (8.2, 8.4, 8.5)
Through our technology we can improve the working conditions of the farmer, allowing him not to perform unnecessary functions, in addition to promoting more sustainable agriculture and by knowing the exact data of the crop he will have an increase in productivity and a reduction in unnecessary expenses.
SDG 10: (10.1, 10.2, 10.3):
Through an inexpensive and collaborative solution, it is possible to reduce inequalities because the same access to data and decision making that a large producer owns a small producer will also obtain.
SDG 12: (12.2, 12.3, 12.4, 12.5, 12.8, 12.a)
Responsible consumption of inputs through optimization of resource use and production.
SDG 13: (13.1, 13.3, 13.b)
With the increase in the possibility of increasing production in sustainable agricultural practices, we are able to help small producers who want to implement environmentally healthy and resilient agricultural systems.
SDG 15: (15.1, 15.2, 15.3, 15.4, 15.6)
Responsible land use through sustainable agricultural management techniques based on data
SDG 17: (17.7)
Through open source and open data programs it is possible to create partnerships for the optimal use of data in order to increase the production and productivity of agricultural properties.
The greatest number of deaths by Covid-19 identified that people with obesity, diabetes and respiratory diseases are at greater risk and this is intrinsically linked to the poor nutritional quality we eat and with intensive agricultural practices and the abuse of the presence of man in nature. We needed to find a balance.
Our main objective is to transform the agricultural system of the small producer, encouraging him to adopt resilient, sustainable practices that contribute to the environment. Allowing these small producers to migrate and / or adapt their production to more friendly production systems and aligned with the preservation of the environment. Seeking greater food security, less interference with nature and greater quality of life for humans.
In Brazil, 50% of farmers have small properties (up to 10 ha) and they are responsible for 80% of the food consumed by the Brazilian people, however only 20% have access to technical knowledge and that is why it motivates us to make a system easy to use, inexpensive and with a decision-making power that only large farmers would once have. Due to COVID 19 its sales fell by up to 80%.
For the development of this project, we spoke with professors from the State University of Campinas in the course of Agricultural Engineering, small farmers, agricultural technicians and local producers.
We used the data made available by NASA to make some mathematical models and studies of trends related to climate, soil moisture, arable area, among others. In our app we will cross-check this data with the data from our robot so that the farmer with the aid of artificial intelligence has an optimization in his production system.
The kit opensource is based in arduino opensource.
Languages: ReactJS, ReactNative, Node.js, Python, HTML, CSS
Softwares: Figma, VSCode, Tableau
Libs: Pandas, Assimv
API: NASA, Meteomatics
Hardware: Arduíno
Sensors: Light, IR, Conductivity, Spectrometer
Others: Material Design, Porkbun
The main challenges we had in this process was to understand the real need of the farmer and what really hurts in his production process, for this we did several interviews of empathy with users to literally put ourselves in their shoes, from this information we were able to use technology to help farmers get better results, as only large farms or groups have access to data that helps them make better decisions. The main achievements of our group was that in fact we were able to cross nasa data with data we obtained from the bibliography and socioeconomics datasets. We built a real and workable prototype and an app that was very intuitive and easy to use. In the next steps we have to train our artificial intelligence so that it can pass on to our user the best possible solutions.
PITCH VIDEO
Link: YouTube
https://earthdata.nasa.gov/learn/pathfinders/agricultural-and-water-resources-data-pathfinder
Terra and Aqua, Soil Moisture Active Passive (SMAP), Land Data Assimilation System (LDAS)
And Meotomatics insights:https://www.meteomatics.com/
Basic Weather Parameters
Derived Weather Parameters:
Climate Trends
Agricultural Parameters
Topography and Land Usage
Agricultural Information Portal:<https://portaldeinformacoes.conab.gov.br/>
How the pandemic damages family farming: <https://www.nexojornal.com.br/expresso/2020/05/11/Como-a-pandemia-causa-um-estrago-na-agricultura-familiar
Is it possible to have harvest predictability?: <https://blog.agrosomar.com.br/previsibilidade-da-colheita/>
Food security and food security: challenges and perspectives from the covid-19: <https://www.migalhas.com.br/depeso/325756/seguranca-alimentar-e-seguranca-do-alimento-desafios-e-perspectivas-a-partir-do-covid-19>
Universal Declaration of Human Rights: <https://nacoesunidas.org/wp-content/uploads/2018/10/DUDH.pdf>
Systematic Survey of Agricultural Production: <https://www.ibge.gov.br/estatisticas/economicas/agricultura-e-pecuaria/21814-2017-censo-agropecuario.html?=&t=resultados>
Countries should mitigate the effects of COVID-19 on trade and food markets, warns FAO: <https://nacoesunidas.org/paises-devem-atenuar-os-efeitos-da-covid-19-no-comercio-e-nos-mercados-de-alimentos-alerta-fao/>
FAO Brazil representative presents scenario of demand for food: <http://www.fao.org/brasil/noticias/detail-events/pt/c/901168/>
Future: The role force of science, technology, and innovation: <https://www.embrapa.br/visao/o-papel-da-ciencia-tecnologia-e-inovacao>
M:ELO, R. R. de. Concepção de um sistema de propulsão elétrica para um trator de 9 KW adequado para agricultura familiar. 2019. 174 f. Tese (Doutorado em Engenharia Elétrica) - Centro de Tecnologia, Universidade Federal do Ceará, Fortaleza, 2019.
With an eye on digital agriculture, Embrapa brings startups closer to investors: <https://economia.estadao.com.br/noticias/geral,de-olho-na-agricultura-digital-embrapa-aproxima-startups-de-investidores,70003222417>
Systematic Survey of Agricultural Production: <https://sidra.ibge.gov.br/tabela/6588>
WHO Manifesto for a healthy recovery from COVID-19: <https://www.who.int/news-room/feature-stories/detail/who-manifesto-for-a-healthy-recovery-from-covid-19>
Levantamento Sistemático da Produção Agrícola - LSPA: <https://www.ibge.gov.br/estatisticas/economicas/agricultura-e-pecuaria/9201-levantamento-sistematico-da-producao-agricola.html>
What is the situation of family farming in Brazil?: <https://www.politize.com.br/agricultura-familiar/>
NASA confirms Embrapa data on planted area in Brazil: <https://www.embrapa.br/busca-de-noticias/-/noticia/30972114/nasa-confirma-dados-da-embrapa-sobre-area-plantada-no-brasil>
Global Forest Watch: <https://www.globalforestwatch.org/>
Challenges in Agroforestry Systems: <http://www.tmeventos.com.br/agrof2016/pdfs/Resumo_palestra_confer%C3%AAncia_Milton_Padovan.pdf>
Scientific work on agroforestry systems implemented in Juruti, Pará, will be highlighted at a world congress in France: <https://g1.globo.com/pa/santarem-regiao/noticia/2019/03/27/trabalho-cientifico-sobre-sistemas-agroflorestais-implantados-em-juruti-no-para-sera-destaque-em-congresso-mundial-na-franca.ghtml>
Replicable agroforestry for the Amazon - PRETATERRA and WRI Brasil
: <http://www.ecoagri.com.br/projeto/agrofloresta-replicavel-para-a-amazonia-pretaterra-e-wri-brasil/>
Science shows the advantages of agroforestry and mixed plantations for restoration: <https://wribrasil.org.br/pt/blog/2019/10/ciencia-mostra-vantagens-de-sistemas-agroflorestais-e-plantios-mistos-para-restauracao>
Ariel Betti: Desenvolvedor Fullstack cursando Sistemas para Internet na FATEC e MBA em Ciência de Dados.
Carlos Henrique Albretch Junior: Agricultural Engineer by UNICAMP. MBA in Strategic Business Management and Integrated Logistics by UNIMAX. Post-graduation in Neuromarketing and Creative Economy and Post-MBA in sales by Inova Business School.
Felipe Ribeiro Tanso: Bachelor of Game Design from Universidade Anhembi Morumbi. Extension in development of 3D games with Unity by PUC-SP. Specialist in Inbound Marketing by Rock Content. Big Data, Machine Learning and Data Mining by FIAP. Advanced Sales Strategies by SB Coaching. CEO of SkyFix Interactive Solutions and PhotoCan.com.br.
Gilson da Silva Domingues: Interaction designer and researcher of rapid prototyping processes, he has been a fellow of the Stanford Fab Learn program since January 2014, Master of Arts by the Arts Institute of the São Paulo State University "Julio de Mesquita Filho" - (UNESP), where he developed research on interfaces tangible features for interactive multimedia installations. He has a specialization in Art History and Contemporary Culture at the same institution (2005) and a degree in Art Education - Full Degree from Montessori College (2004). He is currently a professor in the undergraduate design courses at Centro Universitário Belas Artes in disciplines related to the prototyping of interactive devices.
Nykollas Alves: Fullstack Developer studying Information Systems at Instituto Federal do Sul de Minas - Campus Machado.
Ricardo Ramos: Data scientist and Machine Learning engineer. Graduated in Systems Analysis and currently studying MBA in Data Science.
Special thanks to Prof. Dr. Daniel Albiero, who helped and mentored us as a sponsor on this very special journey that is SpaceApps. Dr. Daniel Albiero, has a degree in Agricultural Engineering from the Faculty of Agricultural Engineering at Unicamp (2001), an incomplete degree in Physics from Unicamp (1996), a master's degree (2005) and a doctorate (2009) in Agricultural Engineering from Unicamp. He is currently Professor of Machine and Robotics Projects at the Faculty of Agricultural Engineering (FEAGRI) at the State University of Campinas (UNICAMP), Extension Coordinator at FEAGRI / UNICAMP. He has experience in the field of Agricultural Engineering, with an emphasis on soil dynamics, design and evaluation of agricultural machinery, agroecological machines, equipment for family farming, optics applied to agricultural engineering, rural buildings with alternative material, physical and mechanical properties of biological material , agricultural aviation, quality management in agriculture, energy in agriculture (biomass and wind) and robotics in agriculture.
