AgriCarer| Better Together
Better Together
Bridging the gap between smallholder farmers and modern technology to reduce knowledge inequality
Summary
Our team is seeking to tackle the knowledge inequality problem currently faced by many small and family-owned farms. It was found that most farmers especially in developing countries are smallholder farmers that lack access to the best agriculture practices, information, and technology. This can lead to problems such as food insecurity, income inequality, and environmental issues.We are proposing a user-friendly smartphone app (AgriCare) to support farmers with state-of-the-art technologies and expert research advice to solve the problem of the knowledge gap.
How We Addressed This Challenge
Our team develop a prototype smartphone application to bridge the gap between smallholder farmers and modern technology. Most smallholder farmers does not have the knowledge and technology to deal with diseases and pests. This is very important issue to address in agriculture as the Food and Agriculture (FAO) of the United Nations estimates that roughly 20% to 40% of crop loss are due to diseases and pests.
The smartphone application (app) serves the purpose of supporting local farmers with modern farming technology to reduce crop losses.
The first feature of the app is the integration of remote sensing technology using open-source data provided by space agencies. The remote sensing functionality of the app utilizes the Multispectral Scanner System (MSS) sensors equipped on satellites. MSS sensors have the ability to capture data at an exceptional spatial resolution as well as determine reflectance in near-infrared. Studies have shown that the electromagnetic data collected by the MSS sensors can be utilised for crop monitoring using vegetation indices (computed by using a combination of electromagnetic data captured).
Vegetation indices can be defined as the indicator that quantifies vegetation biomass and plant vigor for each pixel in a remote sensing image which allows reliable spatial and temporal inter- comparisons of terrestrial photosynthetic activity and canopy structural variations. A few examples of vegetation indices that can be calculated from the data obtained from MSS sensor on satellites are NDVI, MCARI, TCARI and PVI, all of which are capable of relaying some type of useful information about the farm while accurately indicating the affected area.
Our app will provide smallholder farmers with remote sensing based monitoring capabilities to improve the yield of their farms by relaying the area of the farm that requires action to be taken (example: inspection needed as the area of plants is unhealthy) and setting up reminders for the farmers.
The second main feature of the app is the plant diagnosis feature where the app can classify plant diseases from a photo taken. The app will then provide farmers with the immediate action to take, preventative control measures and causes of the disease. These information will ensure that the farmers are well informed to manage the crop and serves as a feature where curated advice from plant pathologists can be shared directly to the farmers in the field.
It is in hopes that the app developed is an accessible medium for farmers globally regardless of wealth and the app can equip all farmers with modern farming technology. In developing nations, this app can play a vital role in preventing food insecurity.
How We Developed This Project
Our team was inspired to choose this challenge after having a conversation with a local farmer over at Malaysia. During our conversation, we were made aware of the challenges faced by many of the local small and family farms due to the gap in knowledge and technology. Knowledge inequality in farming for smallholder farmers was something our team was inspired to address and solve.
We approach developing this project with the knowledge that most smallholder farmers do not have the necessary extra funds to invest in technology and have an aversion to new technology. Therefore, a smartphone app was suggested by the team as it will lower the cost of entry for farmers as most farmers already own a smartphone (and it is relatively cheap), making the technology much easier to adopt for smallholder farmers that need it the most.
We spend most of our time figuring out how to extract the data from NASA/ESA satellites and process multispectral information into useful vegetation indices. We utilised the Sentinel Application Platform (SNAP) program to process the multispectral data as a proof of concept for the remote sensing technology. Besides that, we also utilised Python (FastAI API) to validate our idea on plant disease classification.
The main problem faced by the team with satellite imagery is that we need to process out cloudy days and find days with clear sky in order to extract out useful data for the farmers. We did managed to do an example for a farm of interest in Malaysia which we showcase on our app's prototype.
How We Used Space Agency Data in This Project
Our validation step involves obtaining open data multispectral imagery captured by satellite MSS sensors and processing these images to derive the NDVI index for an area of farmland. The image data extraction and processing are aided by functionalities and software readily available by the European Space Agency (ESA). We source our data directly from the Copernicus Open Access Hub which provides free and open access to imagery captured by the Sentinel satellites launched during the Copernicus program from 2014 to 2015. The Open Access hub allows us to specify to exact regions of interest, satellite sensing periods, and selection of Sentinel imagery required. We then utilise ESA’s Sentinel Application Platform (SNAP) program, which allows the combination of several multispectral data to display satellite images.
As a proof of concept, our team derived one common vegetation index, Normalized Difference Vegetation Index (NDVI) using the software SNAP to customise the combination of light bands to derive useful mapping presentation. In this case, we derive the NDVI mapping by considering the formula, with NIR and Red represented by bands B8 and B4.
NDVI, which measures the amount of green vegetation in an area. NDVI is based on the principle that actively growing green plants strongly absorb radiation in the visible region of the spectrum (the “PAR,” or “photosynthetically active radiation”), while strongly reflecting radiation in the near-infrared (NIR) region. A healthy plant with lots of chlorophyll. NDVI is a standardized way to measure healthy vegetation. When you have high NDVI values, you have healthier vegetation. When you have low NDVI, you have less or no vegetation and good cell structure will actively absorb red light and reflect near-infrared.
In our instance above, we defined our spectrum of low NDVI (represented by yellow) and high NDVI (green). Greener regions, i.e towards the end of the spectrum suggests healthier vegetation and yellowish regions suggest the contrary.
Project Demo
YouTube Video:
https://youtu.be/j6hRNewuG94
Data & Resources
Satellite Imagery (ESA): https://scihub.copernicus.eu/dhus/
PlantVillage: https://github.com/spMohanty/PlantVillage-Dataset