Taking Farming to New Heights: Detecting Soil-Borne Illnesses with Precision Farming

First of all, before we begin, I would just like to thank my wonderful team members Shirley Yang, Ami Shah, Jula He, and Shimoi Kalra. Terra truly would not be a possibility without each and every one of you!

Picture this.

You’re walking through a beautiful field of crops, enjoying the fresh air and the beauty of nature around you. Suddenly, you notice a leaf drop.

Your eyes lock onto the plant’s failing stem, which was once robust and resilient but now weakened. The lush greenery that once adorned its boughs is now slowly wilting away, as the tips of the leaves gradually turn into a feeble, yellowish color. You can see the fragility of the twigs that hold the leaves, as hairline cracks traverse their length, revealing the extent of their deterioration.

It’s a stark reminder that even something as seemingly idyllic as a field of crops can pose serious health risks.

The Problem

An Overview of Soil-Borne Illnesses

25% of the global burden of disease is attributable to environmental factors, including soil-borne illnesses. (World Health Organization)

Soil-borne illnesses — infections caused by microorganisms that lurk in the soil. These tiny organisms can wreak havoc on humans, animals, and plants that come into contact with contaminated soil.

Soil-borne illnesses are a big deal. They cause serious health problems such as vomiting, fever, and even death.

Soil-transmitted helminth (STH) infections are among the most common infections worldwide with an estimated 1.5 billion infected people or 24% of the world’s population.

This is a real concern in areas with poor sanitation, where people may be exposed to contaminated soil while farming or participating in other outdoor activities.

These infections affect the poorest and most deprived communities with poor access to clean water, sanitation and hygiene in tropical and subtropical areas, with the highest prevalence reported from sub-Saharan Africa, China, South America and Asia.

What Causes Soil-Borne Illnesses?

Soil-borne illnesses are caused by microorganisms that live in the soil and infect the roots or other parts of the plant. These microorganisms include bacteria, fungi, viruses, and parasites.

Soil Microbes and Their Effects on Animals and Humans

Microorganisms in soil are introduced through natural processes and human activities.

• Natural Processes → Decay of organic matter and the activities of living organisms can introduce microbes to soil.
• Human Activities → Agricultural practices, use of contaminated water or soil amendments can also introduce pathogens to soil.

Once introduced, microorganisms can persist in soil and form complex interactions with other organisms, affecting plant health and the soil ecosystem.

When a plant grows in soil that is contaminated with these microorganisms, the microorganisms can enter the plant through the root system. The microorganisms may then multiply and spread within the plant, causing various types of diseases that can affect the growth and health of the plant.

Schematic of microbiome surrounding a plant throughout its life history

In the case of bacterial and fungal infections, the microorganisms may secrete enzymes or toxins that damage the plant cells and tissues, leading to symptoms such as wilting, yellowing, or necrosis (tissue death).

These infections weaken the plant’s immune system, making it more susceptible to other types of infections or environmental stresses.

How Does This Impact Us?

Soil-borne illnesses have an immense impact on people and surrounding communities. Whether it's through direct or indirect consumption, it's a problem that trickles down to everybody, because… we all need food to survive.

Directly → Consumption of Contaminated Plants

When people consume or come in specific contact with contaminated plants or plant products, such as fruits, vegetables, grains, or nuts. Those contaminated plants carry harmful microorganisms that can cause illness when ingested.

Some of the most common and well-known examples of soil-borne pathogens are:

• Salmonella → A group of bacteria commonly found in the intestines of animals. Causes food poisoning and can survive in soil for months to years.
• Escherichia coli → A strain of E. coli that can cause severe gastrointestinal illness, including bloody diarrhea, abdominal cramps, and vomiting. It’s commonly associated with contaminated ground beef but can be found in soil and water.
• Clostridium tetani → A spore-forming bacterium that causes tetanus, a serious disease that affects the nervous system. C. tetani spores can persist in soil for many years and can enter the body through puncture wounds, such as those caused by rusty nails or animal bites.
• Bacillus anthracis → A spore-forming bacterium that causes anthrax. Anthrax spores can survive in soil for decades and can enter the body through cuts or abrasions in the skin or by inhalation of spores.
• Histoplasma capsulatum → A fungus that causes histoplasmosis, a respiratory disease. H. capsulatum spores are found in soil contaminated with bird or bat droppings and can be inhaled, causing lung infections.
• Toxoplasma gondii → A parasite that can cause toxoplasmosis. T. gondii is commonly found in soil contaminated with cat feces and can be transmitted through the ingestion of contaminated food or water.

Indirectly → Soil-borne Illnesses Affect Agricultural Production and Food Security

Soil-borne illnesses in plants affect agricultural production and food security.

When plants are infected or damaged by soil-borne microorganisms, their yields are reduced and their quality is compromised. This leads to economic losses for farmers and reduced availability or affordability of food for local communities/consumers.

Why Does this Problem Matter?

Over 260 million preschool-age children, 654 million school-age children, 108 million adolescent girls, and 138.8 million pregnant women live in areas where these parasites/diseases are intensively transmitted and are in need of treatment and preventive interventions.

Impact on Public Health

Bacterial pathogens, fungal toxins, parasitic infections

• Bacterial pathogens, such as Salmonella and E. coli, cause acute diarrhea, fever, and abdominal pain, and can lead to complications such as dehydration and kidney failure.
• Fungal toxins, such as aflatoxins, can accumulate in the liver and cause damage over time, leading to liver cancer and other health problems.
• Parasitic infections, such as those caused by hookworms and other nematodes, can lead to anemia, malnutrition, and cognitive impairments.

Impacts on Food Security and Society

Food Security

• When plants are infected with soil-borne pathogens, their yields are reduced or their quality is compromised, reducing the availability or affordability of food for consumers.
• Soil-borne illnesses can lead to the loss of soil biodiversity and ecosystem services, which can have far-reaching impacts on environmental health and social well-being.
• In most regions, soil-borne illnesses are particularly prevalent and pose a significant threat to public health and food security, exacerbating existing inequalities and poverty.

Soil-borne illnesses are a major threat to the food we grow and eat. These microorganisms cause plant diseases that lead to crop failures, reducing the availability and affordability of food for communities.

What Makes This Problem so Difficult to Solve?

Transmission and Detection

Transmission

• Time Persistence → Soil-borne pathogens can persist in the soil for long periods, making it difficult to eradicate them completely.
• Multiple Paths of Transmission → Soil-borne pathogens can be spread through various routes, including contaminated soil, water, plant material, or animal feces.
• Environmental Persistence → Soil-borne pathogens can survive in harsh environmental conditions, such as high or low temperatures, pH extremes, or low oxygen levels, making them resilient to many disinfection or sanitation methods.
• Complex Relationships → Soil-borne pathogens can also interact with other soil microorganisms, such as fungi and bacteria, and form complex relationships that may affect their persistence and transmission.

Detection

Transmission pathways of infection or pathogenic microbes

• Non-visible Markers → Soil-borne pathogens can be difficult to detect, as they may not always cause visible symptoms or damage to the plant or soil.
• Extensive Testing → Soil samples may need to be tested extensively to detect the presence of soil-borne pathogens, which can be time-consuming and expensive.
• Low Concentrations → Soil-borne pathogens may also be present in low concentrations, making them difficult to detect using conventional methods.

To overcome these challenges, it is important to adopt a multi-disciplinary approach that combines different strategies for prevention, detection, and management of soil-borne illnesses.

Specifically monitoring soil health and disease outbreaks through regular soil sampling and testing.

How do Farmers Detect Soil-borne Diseases in the Status Quo? / What are the Current Solutions?

1. Visual inspection: Farmers may observe their crops for signs and symptoms of disease, such as wilting, yellowing, stunting, or lesions on leaves, stems, or roots. These symptoms can help diagnose certain soil-borne diseases, such as Fusarium wilt or Rhizoctonia root rot.
2. Soil testing: Farmers may take soil samples from their fields and send them to a laboratory for analysis. Soil tests can provide information on soil properties, nutrient levels, and the presence of soil-borne pathogens or other pests.

For example, farmers may use a PCR (polymerase chain reaction) test to detect the DNA of specific soil-borne pathogens, such as Pythium or Phytophthora.

The ineffectiveness of current methods for detecting soil-borne diseases is the factor of convenience. Testing for soil-borne diseases can be time-consuming and expensive, and farmers may not always have the resources or incentives to do so regularly.

This can lead to a lack of awareness about the presence of soil-borne pathogens, which can then contribute to the spread of diseases.

For example, if farmers are not regularly testing their soil for soil-borne pathogens, they may not detect the presence of a disease until it has already caused significant damage to their crops. This can make it more difficult to control the disease and may result in lower yields or even crop failure.

This leads to incomplete detection. Some soil-borne pathogens may be difficult to detect using conventional methods, especially if they are present in low concentrations or have complex interactions with other microorganisms in the soil.

This means that even if farmers are able to identify certain diseases in their crops, they may not be able to detect all of the pathogens that are present in the soil.

Let’s narrow it down.

• Soil-borne diseases affect millions of people and surrounding communities.
• It's a problem that’s also really difficult to solve because current solutions are inconvenient, ineffective, and expensive.

The WHO strategy for control is to control morbidity through the periodic treatment of at-risk people living in endemic areas. But...

What if we could detect soil-borne illnesses before they even spread?

Early detection is crucial in preventing soil-borne illnesses. It allows for prompt action to be taken to prevent their spread and minimize their impact.

For example: Contaminated water sources can be treated or alternative sources provided, and infected crops can be quarantined or rotated.

Early detection helps identify high-risk groups and improves surveillance and monitoring, informing public health policies and interventions to prevent future outbreaks.

It's the key strategy for protecting public health from soil-borne illnesses.

Worldwide, an estimated 20–40% of crop yield is lost to pests and diseases, and that’s because they go undetected.

Soil-borne illnesses are a silent yet deadly menace that wreaks havoc on millions of lives worldwide. These illnesses, are caused by tiny, but potent microorganisms that lurk in soil, water, and food, waiting to strike unsuspecting victims. Among the most prevalent soil-borne illnesses are salmonellosis, listeriosis, and E. coli infections, which can cause debilitating health problems and even death.

Given the grave and pervasive nature of soil-borne illnesses, there is an urgent need for innovative solutions to address this problem and improve public health outcomes

The Solution | Terra

Detecting Soil-Borne Illnesses with Precision Farming

Overview of Terra

Terra drones are equipped with high-resolution cameras and sensors that can revolutionize the way farmers and researchers approach agriculture. With the ability to collect detailed data on soil-borne illness biomarkers such as soil moisture, and nutrient levels. This makes Terra a powerful tool for identifying areas of soil contamination and taking preventative actions.

These drones monitor crop growth and health, enabling farmers to optimize yields while reducing the risk of soil-borne illnesses. Through the use of precision farming techniques like these, we can reduce the use of harmful chemicals, improve soil health, and promote sustainable agriculture practices that protect public health and the environment.

How Does The Terra Drone Work?

There are 4 steps Terra carries out to mass effectively detect soil-borne illnesses in local or industrial farms.

1. Sensor data collection → Drones equipped with high-tech sensors and cameras are flown over farmland to capture detailed images and data on soil moisture levels, nutrient content, and pH levels, among other key factors affecting soil quality.
2. Geographic Information Systems (GIS) analysis → The data collected by the drones is analyzed using GIS to map and analyze soil characteristics, such as pH levels, organic matter content, and nutrient distribution, which can help identify areas of potential contamination.
3. Computer vision analysis → Computer vision algorithms are used to analyze drone-captured images to detect changes in plant health, which can indicate the presence of soil-borne pathogens.
4. Durability and Design → Solar panels are used to power the drones, reducing their reliance on non-renewable energy sources and enabling longer flight times and more extensive data collection.

1. Sensor Data Collection → Detecting Soil-borne Illness Biomarkers

Plant Stress Biomarkers

Biomarker-based detection methods can be highly specific and sensitive, allowing for the rapid and accurate identification of soil-borne pathogens, even in cases where symptoms are not yet visible.

Detecting soil-borne illness biomarkers involves identifying specific molecules or proteins that are produced by soil-borne pathogens, which can serve as diagnostic indicators for the presence of these pathogens in the soil.

Terra uses 2 types of sensors: hyperspectral sensors and RGB cameras for monitoring the soil.

Hyperspectral Sensors → Spectral sensors work by measuring the reflectance of light by plants in different wavelengths, which can provide information on plant health and nutrient levels.

Hyperspectral Sensors in Farming

Spectral sensors can be compared to a prism that separates light into its different colors. By measuring the reflectance of light by plants in different wavelengths, spectral sensors can provide information on plant health and nutrient levels, helping to identify areas of the field that may be at risk of disease.

Still don’t get it?

This sensor shoots down light and can differentiate high precision light measurements. By picking out different light properties, it can identify areas with more water content, which may lead to the detection of soil-borne illnesses. Hyperspectral analysis can detect different types of light based on the different properties in the ground and identify hot spots or darker areas where soil-borne illnesses are more likely to be found.

Specific Biomarkers Terra Drone’s hyperspectral sensors will be focusing on:

1. Changes in chlorophyll content — Soil-borne pathogens cause chlorosis or a reduction in chlorophyll levels in infected plants, which can be detected through changes in spectral reflectance.
2. Fungal spores — Soil-borne fungi produce characteristic spores that can be detected through their unique spectral signatures.
3. Nitrogen content — Changes in soil nitrogen content indicate the presence of certain soil-borne pathogens, such as Fusarium species.
4. Plant stress responses — Some soil-borne pathogens can induce stress responses in infected plants, such as the production of certain secondary metabolites or changes in gene expression patterns, which could be detected through hyperspectral imaging.

Hyperspectral Sensor Imaging

This can be used to detect the presence of pathogens or nutrient deficiencies that can contribute to the spread of soil-borne diseases. For example, changes in reflectance patterns can indicate the presence of chlorosis, which is a symptom of nutrient deficiency

Hyperspectral sensors can measure various parameters, such as soil moisture, soil temperature, and soil texture. Providing a comprehensive approach to detecting soil-borne illnesses at an early stage.

RBG cameras → RGB cameras are used to capture high-resolution images of plants and soil from the drone’s perspective.

RGB cameras capture information within the visible light spectrum, which is useful for identifying visual symptoms of soil-borne illnesses, such as yellowing or wilting of leaves. RGB images are used in conjunction with other sensor data, such as hyperspectral to provide a more comprehensive analysis of soil and plant health.

2. Geographic Information Systems (GIS) Analysis

Geographic Information Systems Analysis includes optimizing flight paths using AI and data acquisition.

Flight Path Optimization

Geographic Information Systems (GIS) Analysis

The drones used for soil monitoring would be equipped with GPS and imaging sensors, which would enable them to map the agricultural land and plan flight paths. Advanced flight planning software is used paired with Artificial intelligence algorithms, which can take into account factors such as wind speed and direction, terrain elevation, and the location of obstacles.

Artificial intelligence algorithms (specifically RNNs recurrent neural networks) are used to optimize flight paths, ensuring maximum coverage of the land while minimizing flight time and battery usage.

Recurrent Neural Networks (RNNs) are a type of neural network that are particularly well-suited for sequential data processing tasks, where data is processed in a specific order or sequence.

This is done by considering factors such as wind speed and direction, terrain, and the drone’s battery life. The neural network can learn and adapt to different field conditions and environmental factors, improving its performance over time.

Recurrent Neural Network Diagram for Mapping Flight Path

The RNN can be trained on a sequence of flight paths and associated sensor and camera data to learn patterns and relationships between different features. This allows the RNN to predict the optimal flight path for the next iteration based on the previous flight path and sensor data.

For example, during the first flight, the drone may collect sensor and camera data and fly in a specific pattern. The RNN can then analyze this data and generate a model that predicts the optimal flight path for the next iteration based on the previous data. As the drone continues to fly and collect data, the RNN can continually refine its model and generate increasingly accurate predictions for future flight paths.

This is especially important for larger farms that span over long distances while maximizing efficiency and limiting costs.

Data Acquisition

To optimize flight patterns and ensure maximum coverage, a combination of 20 to 30 drones can be used to capture images of the farmland. The drones will fly overlapping patterns to correct for errors caused by noise and backscatter. Once the drone imagery is obtained, soil samples must be taken to validate the observations made by the drones. Soil samples should be collected from 50 random points to determine where soil-borne illnesses are present.

Drone Overlap Data

The platform used for this work will be Python and R language. In Python, geopandas is used along with packages that provide a set of commands that can be used for data analysis, such as fiano raterui. R language has two packages, sf and terra, that can be used for geospatial data analysis.

The sensors would need to be calibrated before each flight to ensure accurate measurements. The data collected would be stored on-board the drone or transmitted to a central database for further analysis. To ensure data quality, the drones may also be equipped with real-time quality control checks and automated error detection systems.

3. Computer Vision Analysis → Data processing

The collected data is used to generate a map of the field, highlighting areas that need closer inspection due to the presence of soil-borne diseases or nutrient deficiencies.

The QGIS platform is used in this process, to classify where the soil-borne illness is. Darker areas being more likely to have soil-borne illnesses.

Then, machine learning (CNN) is applied to predict the likelihood of soil-borne illnesses being present based on conditions in the soil. Before this, preprocessing is required using GIS to transform the images to account for atmospheric changes, such as light going through the atmosphere and back scatter or noise.

The data needs to be corrected to take these factors into account, and the GIS format allows for easy cleaning of data later on.

Convolutional Network

When it comes to the machine learning classification process, pixels can be changed using algorithms, which can then be applied to RGB and multispectral images.

Pictures taken by drones can be analyzed using RGB to detect changes in plant health, which can indicate the presence of soil-borne pathogens. By applying machine learning algorithms to the image data, it’s possible to classify areas of the soil based on the presence or absence of soil-borne illnesses.

Point Cloud

A point cloud is generated by taking many pictures of a single area with overlap, resulting in a 90% overlap of multiple images stacked upon each other. This allows the conversion of a 2D image into a 3D image. Point clouds are particularly important for soil and vegetation mapping, especially for areas with smaller crops.

They are essential for identifying where crops are, as the size of the crops may be smaller than other crops in the area.

4. Durability and Design

Flexible solar panels are used to power the drones, reducing their reliance on non-renewable energy sources and enabling longer flight times and more extensive data collection.

Flexible Solar Panels

The drones will be exposed to harsh environmental conditions while flying over agricultural fields. The drones should be able to withstand extreme weather conditions, including strong winds and rain.

The use of solar panels help reduce the weight of the drones by reducing the size of the battery needed.

How Will This Help Farmers On The Ground?

The Terra app will display a dashboard with various metrics such as soil moisture, nutrient levels, and pathogen presence. The data can be presented in an easy-to-understand format, such as graphs, charts, or maps, allowing farmers to quickly identify areas of concern and take action.

• Recommendations: Based on the data analysis, scientists can provide recommendations to farmers on appropriate actions to take to prevent the spread of diseases and promote healthy soil. These recommendations are generated automatically using artificial intelligence algorithms, which can take into account factors such as the type of crop, soil type, and weather conditions. In addition, data visualization techniques can be used to present the recommendations in a clear and concise manner.
• Monitoring: The drones can be used to monitor crop growth and health, allowing farmers to optimize their yields while reducing the risk of soil-borne illnesses. The drones would be equipped with high-resolution cameras and spectral sensors, which would allow them to capture detailed images of the crops. Advanced image processing techniques can be used to analyze the images and identify any issues, such as nutrient deficiencies or pest infestations. In addition, real-time monitoring can be used to provide early warning of any issues, allowing farmers to take action before the crops are severely impacted.

For example, if the data indicates that there is a high level of a particular pathogen in a certain area of the field, the farmer may decide to apply a targeted treatment, such as soil sterilization or biocontrol agents. Similarly, if the data shows that there is a low level of nutrients in a certain area, the farmer may decide to adjust their fertilizer application practices to promote healthy soil.

In addition, the app or platform may provide recommendations generated by artificial intelligence algorithms based on the data analysis. These recommendations may include specific actions that the farmer can take to promote healthy soil and prevent the spread of diseases.

The farmers can also use the data to optimize their yields by monitoring crop growth and health.

For example, the app provides insights on when to irrigate or fertilize the crops to ensure they are receiving the necessary nutrients and moisture.

The farmers can also monitor the crops for any issues, such as nutrient deficiencies or pest infestations, allowing them to take action before the crops are severely impacted.

The Impact of Terra

A Terra drone can see 1,500–2,000 feet away during the day. At night, drone cameras can pick up an image about 165 feet away before its sensors become blurry.

Scanning 20 meters per second, for an average Canadian farm of 234 acres, it would take…

8 minutes and 12 seconds to finish the scan of the whole entire farm.

Increased efficiency and productivity: By using drones to collect data on soil moisture, nutrient levels, and crop growth and health, farmers can optimize their yields while reducing the risk of soil-borne illnesses. This will lead to increased efficiency and productivity in agriculture, allowing farmers to produce more food with less resources.

By detecting soil-borne illnesses before they even become a threat based on AI predictions and early detections.

Reduced environmental impact: The use of targeted treatments such as soil sterilization or biocontrol agents can reduce the use of harmful chemicals and pesticides, reducing the environmental impact of agriculture. Additionally, by adjusting irrigation and fertilization practices based on data analysis, farmers can minimize soil erosion and nutrient runoff, further reducing the impact on the environment.

Improved public health: Soil-borne illnesses can have a significant impact on public health, and the use of drones for precision farming can help identify areas of soil contamination and prevent the spread of diseases. By promoting healthy soil, farmers can also produce healthier crops, which can have a positive impact on public health.

The use of drones for precision farming has the potential to revolutionize agriculture by improving efficiency, productivity, and sustainability while reducing the environmental impact of agriculture and promoting public health. However, there are also possible downsides and risks, including the cost of the technology, data privacy and security, technical limitations, dependence on technology, and regulatory challenges. It is essential for farmers and researchers to be aware of these challenges and work to address them to ensure the safe and effective use of drones for precision farming.

The use of drones for precision farming has the potential to drive further discoveries and advancements in agriculture and technology. By continually refining and improving the technology, researchers and farmers could unlock new insights and approaches to sustainable and productive agriculture practices.

Acknowledgments

I would like to thank my wonderful teammates: Shirley Yang, Ami Shah, Jula He, and Shimoi Kalra.

Thank you so much for reading our article, Taking Farming to New Heights: Detecting Soil-Borne Illnesses with Precision Farming, and learning about the future of food and precision farming!

Farming

Drones

Plants

Soil Health

Precision Agriculture