AI Insights

Success in Water Management and Plant Health Prediction with Drone Technology – Our AI is Revolutionizing Agriculture

May 27, 2024


article featured image

Photo credit: Sergio Merino Dominguez


Author of an article: Weronika Dorocka – VP of Business Development

Introduction

In a world where climate change and resource scarcity threaten our way of life, innovative solutions are essential for sustainable development. This success story tells a story of a promise for the future that we all need, the future where resources are not wasted and the problems are smartly detected to act effectively and fast. We harnessed advanced drone technology to optimize water consumption and predict plant health in agricultural fields. 

Understanding the Initial Problem

All initiatives that center around plants, including but not limited to the agricultural sector, often struggle with two significant issues: inefficient water usage and the difficulty of accurately monitoring plant health.

Agriculture often faces two critical challenges: inefficient water use and difficulty in accurately monitoring plant health. Over-irrigation wastes water and increases costs, while under-irrigation harms crops. Traditional plant health monitoring is labor-intensive and prone to errors, missing early signs of disease and stress. These inefficiencies lead to higher costs and lower yields, threatening sustainability. Optimizing water use and enhancing plant health monitoring can save significant costs, improve crop yields, and contribute to sustainable farming practices.

The Benefits of Our Solution

Optimized Water Usage: By precisely targeting irrigation, we achieved significant water savings, contributing to sustainable farming practices and cost reductions.

Enhanced Plant Health: Early detection and mitigation of water stress and other health issues resulted in more resilient and productive crops.

Increased Efficiency: Automated monitoring and analysis reduced the labor and time required for field inspections, allowing farmers to focus on other critical tasks.

Our Innovative Solution

Recognizing these critical pain points, our team developed three pioneering models, utilizing advanced multispectral drone data to provide precise, actionable insights:

1. Creating a New Precision Standard in Irrigation Systems

Soil Moisture Index (SMI) Estimation using the Triangle Method: This model accurately measures soil moisture levels, allowing farmers to make informed irrigation decisions. By applying water precisely when and where it’s needed, we minimized water waste and ensured that plants received optimal hydration, leading to healthier crops and increased yields.

2. Detecting and Preventing Water Stress and Waterlogging (too much, too little water in specific parts)

Threshold-based Model for Identifying Water Stress and Waterlogging: This model sets specific thresholds to detect areas where plants are either receiving too little water (water stress) or too much water (waterlogging). Early identification of these conditions enables farmers to take corrective actions, such as adjusting irrigation schedules or improving drainage systems. This proactive approach prevents crop damage and maintains plant health.

3. Advanced Health Monitoring: Grouping Plants by Health Status with K-Means Clustering

K-Means Clustering Model for Health Monitoring: This model groups plants based on their health status, providing a clear, detailed picture of the field’s overall condition. By monitoring these clusters, farmers can quickly identify and address issues such as diseases or nutrient deficiencies in specific areas, ensuring targeted and effective interventions.

Discover how we did it!

The Background 

Plants make up 80% of the food we eat and produce 98% of the oxygen we breathe.

From feeding a growing world population to protecting biodiversity and ecosystems, the significance of plants is tremendous. Consequently, the protection of plants is paramount. In an era of changing climate, rising temperatures, and threats like hungry locusts, the preservation and health of plants have never been more important.

How Plant Health and Hydration Are Commonly Monitored

Traditionally, monitoring plant health and hydration has relied on several methods:

  1. Visual Inspections: Farmers and agronomists walk through fields to visually assess plant health. This method is labor-intensive, time-consuming, and subjective, often missing early signs of stress or disease.
  2. Soil Moisture Sensors: Ground-based sensors measure soil moisture levels at specific points. While accurate, these sensors cover limited areas and may not capture the full variability of field conditions.
  3. Satellite Imagery: Satellites provide large-scale images of crop fields, but their resolution is often too low to detect small-scale issues. Additionally, cloud cover can obstruct satellite imagery, limiting its effectiveness.
  4. Manual Sampling: Collecting soil and plant samples for laboratory analysis provides detailed information but is labor-intensive and time-consuming. This method also only represents specific sampled locations and may not reflect broader field conditions.

The Goal 

We started with an aim to build an automated plant health prediction and monitoring solution using drone-derived multispectral and thermal data.

Our Approach

Preparation Steps: 

Step 1. 

Identifying the Need for a Test Environment and Its Requirements

Before choosing the right testing environment, we identified the essential components required for our project:

  1. Variation in Environmental Conditions: A test environment with diverse conditions, including varying levels of moisture, salinity, and temperature, was crucial. This variation would help us develop and validate our models under different scenarios.
  2. Existing Sensor Infrastructure: Having a location with pre-installed sensors to monitor soil moisture and other relevant parameters would facilitate cross-referencing and validating our drone data.
  3. Accessibility for Field Data Collection: The ability to easily collect ground-truth data, such as soil moisture levels and plant health indicators, was necessary for accurate model training and validation.

Step 2. 

drone

The Choice of a Case Study Environment: A Golf Course

While a farm field might seem like an obvious choice, we selected a golf course for several compelling reasons:

  1. Controlled Environment: A golf course provides a controlled environment with consistent maintenance practices. This consistency made it easier to isolate and study specific variables without the interference that might come from varying agricultural activities on a farm.
  2. High Variation in Conditions: Golf courses have significant variation in moisture and salinity levels due to different watering practices for fairways, greens, and roughs. This variation is ideal for testing our models, as it simulates different stress conditions that crops might experience.
  3. Existing Infrastructure: Many golf courses already have advanced sensor infrastructure in place to monitor soil moisture and other conditions. This existing infrastructure allowed us to cross-reference and validate our drone data effectively, providing a reliable and efficient testing environment.
  4. Dynamic Conditions: Golf courses experience diverse conditions due to seasonal changes, weather patterns, and resource provision (water, nutrients). This diversity made them perfect for testing our approach under varying scenarios and ensuring the robustness of our models.
  5. Ease of Data Collection: The structured layout of a golf course and the existing maintenance routines facilitated easier and more consistent collection of ground-truth data. This was critical for validating our model predictions accurately.

Knowing All That,
Why using Drones in our Solution?

Disease in chili plant.

The drones we decided to use are equipped with advanced multispectral and thermal sensors that capture a range of data across different spectral bands. In this context, “bands” refer to specific ranges of wavelengths in the electromagnetic spectrum that the sensors can detect.  These specialized drones, can detect subtle differences in plant health and soil conditions from a distance. The multispectral sensors capture light in the blue, green, red, red edge, and near-infrared bands, providing detailed information about plant vigor and stress.

  • The blue, green, and red bands capture visible light similar to what the human eye can see, helping assess general plant health. 
  • The red edge band captures light just beyond the visible red spectrum, which is crucial for detecting changes in chlorophyll content that indicate plant stress. 
  • The near-infrared (NIR) band captures light that is highly reflective in healthy vegetation, helping to assess plant biomass and health. 
  • Its thermal sensors measure the surface temperature of the plants and soil, which helps identify areas of water stress and waterlogging. These high-resolution sensors enable drones to detect small details in plant health and hydration that would be difficult to observe with the naked eye or traditional methods, making them ideal for precise agricultural monitoring.

Here we also decided to give a bit of comparison between other common techniques and our choice:

Visual Inspections vs. Drones:

  • Visual Inspections: Labor-intensive, subjective, and can miss early signs of issues.
  • Drones: Provide high-resolution, objective data that covers large areas quickly and can detect early signs of stress or disease that might be missed during visual inspections.

Satellite Imagery vs. Drones:

  • Satellite Imagery: Covers large areas but with lower resolution and potential issues with cloud cover.
  • Drones: Provide high-resolution, real-time imagery unaffected by cloud cover, allowing for detailed analysis of specific areas.

Manual Sampling vs. Drones:

  • Manual Sampling: Provides detailed information but is labor-intensive and time-consuming, covering only specific points.
  • Drones: Can quickly cover large areas and provide detailed data on soil and plant health, reducing the need for extensive manual sampling.

Why Use Drones Instead of Ground Sensors you may think? 

  1. More Comprehensive Coverage: Drones can cover large areas quickly and efficiently, providing comprehensive data across the entire golf course. Ground sensors, while useful, are limited to specific locations and may miss variations in other parts of the field.
  2. High-Resolution Data: Drones equipped with multispectral and thermal sensors capture high-resolution images and data that ground sensors cannot match. This detailed data allows for more precise analysis and better identification of problem areas.
  3. Flexibility and Accessibility: Drones can easily access areas that might be difficult or impractical to reach with ground sensors. This ensures that no part of the golf course is left unmonitored.
  4. Real-Time Monitoring: Drones can provide real-time data and imagery, allowing for immediate analysis and decision-making. Ground sensors typically require data retrieval and processing, which can delay response times.
  5. More Cost-Effective for Scaling: Deploying drones is often more cost-effective than installing and maintaining a large number of ground sensors across a field. Drones can be easily deployed as needed without the extensive setup and maintenance required for ground-based systems.

Our AI Approach 

Step 1: Understanding the Dataset and Problem Analysis

What We Did:  The dataset provided to us consisted of multispectral drone imagery of a 7 month time frame, spanning different seasons and weather conditions. The seven bands were captured using Altum sensors from MicaSense, which include Blue, Green, Red, Red Edge, Near-infrared, Thermal, Transparency. Additionally, field scouts of soil moisture survey data were provided. We began by thoroughly understanding the dataset and the problem at hand. We also had a detailed discussion with a domain expert,, to understand specific needs and expectations of the industry.

Step 2: Setting Up a Framework for Moisture Measurement – Soil Moisture Index (SMI) Estimation

Important Aspects:

  • NDVI (Normalized Difference Vegetation Index): This index measures plant health by comparing the amount of reflected light in the red and near-infrared bands. Healthy plants reflect more near-infrared light and less red light, while stressed plants reflect less near-infrared light and more red light. NDVI values range from -1 to +1, where higher values indicate healthy vegetation and lower values indicate stressed or sparse vegetation.
  • Thermal Data: Thermal sensors measure the surface temperature of the plants and soil. Cooler areas usually indicate healthy, well-watered plants, while hotter areas can signal water stress. This temperature data helps us understand the thermal conditions of the plants and soil.
  • SMI Calculation: By combining NDVI and thermal data, we created a Soil Moisture Index (SMI). This index indicates how much moisture is in the soil, helping to identify areas that are either too dry or too wet.

What We Did: We integrated thermal data with the Normalized Difference Vegetation Index (NDVI) to identify areas of water stress (where plants are too dry) and waterlogging (where plants have too much water). The SMI was calculated using the Red, Near-Infrared, and Thermal bands from the drone data.

Process:

  1. Data Understanding: We started by reviewing the NDVI and thermal data from the drones to understand the current conditions.
  2. Scatterplots: We created scatterplots (graphs) plotting temperature against NDVI values to identify patterns. This helped us find “dry edges” (hot, dry areas) and “wet edges” (cool, wet areas).
  3. Downsampling: We reduced the size of the data to remove noise and make processing faster and more efficient.
  4. Output: We generated an SMI map that visually shows areas of water stress and waterlogging.
Temperature and soil moisture

Figure 8: Temperature and soil moisture field data points and NDVI, Thermal and SMI prediction of the greens on Hole #2, 2021.06.16 (Source: Omdena)

Step 3: Ensuring Accuracy through Validation – Field Data Comparison and Accuracy Scatterplots

What We Did: Validation is a crucial step to ensure the accuracy and reliability of our Soil Moisture Index (SMI) predictions. It involves comparing the SMI predictions with actual field data and fine-tuning the model based on these comparisons.

Why It Was Needed: Validation is needed to confirm that our model’s predictions are accurate and trustworthy. By comparing the SMI values generated by the model with actual soil moisture readings, we can identify any discrepancies and make necessary adjustments to improve the model’s performance.

Validation Process:

  • Field Data Comparison: We compared the SMI predictions with actual soil moisture data collected manually. This step is essential to ensure that our model accurately reflects the real conditions on the ground.
  • Accuracy Scatterplots: We created scatterplots comparing the predicted SMI values to actual soil moisture readings. These scatterplots helped us visualize the accuracy of our model and identify areas where it needed fine-tuning. By analyzing these scatterplots, we could adjust our model to improve its predictive accuracy.

Step 4: Identifying Problem Areas to Target Interventions – Threshold-Based Model

Important Aspects:

  • Thresholds: Thresholds are specific values that help the model decide whether an area is healthy, water-stressed, or waterlogged. These values are derived from the data to classify different conditions accurately.
  • Data Processing:
    • Downsampling: Reduced image resolution to speed up processing.
    • Rescaling: Adjusted image values to a standard scale for easier analysis.
    • Masking: Focused on specific areas of interest by applying masks to the images.
    • Polygonization: Converted image data to vector format for detailed analysis and visualization.
    • Thresholding: Applied the thresholds to identify problem areas based on the data.

What We Did: We developed a model that sets specific thresholds to detect areas with water stress and waterlogging.

Results:

  • The model accurately identified water-stressed and waterlogged areas. This allowed for targeted interventions to improve plant health and optimize water usage.
Waterlogged regions on Fairway 2 from 16-06-2021. Left: RGB image, Right: Identified waterlogged regions (Source: Omdena)

Waterlogged regions on Fairway 2 from 16-06-2021. Left: RGB image, Right: Identified waterlogged regions (Source: Omdena)

Step 5: Grouping Plant Health Status for Effective Monitoring – Clustering Model

Important aspects:

  • Clustering: Clustering groups similar data points together. Here, it grouped areas of the golf course based on plant health. This helps in identifying patterns and regions that need specific attention.
  • Data Processing:
    • Masking: Isolated areas of interest on the golf course.
    • Filtering: Removed outliers to focus on meaningful data and reduce noise.
    • Scaling: Standardized data for better clustering by normalizing the values.
    • Clustering with K-Means: Applied the K-Means algorithm to categorize the areas into clusters based on health status. K-Means is a method of vector quantization that partitions the data into k clusters, each represented by the mean (centroid) of the data points in the cluster.
  • Post-Processing:
    • Sieve: Removed small, insignificant clusters to focus on the most relevant areas.
    • Polygonization: Converted clusters to vector format for easy visualization and interaction.

What We Did: We used clustering algorithms to group plants based on their health status.

Results:

  • Visualization: The clustering results provided a clear visual representation of plant health across the golf course. Different clusters indicated varying levels of plant health, from healthy to stressed.
  • Actionable Insights: Craig could quickly identify and address problem areas, ensuring targeted interventions and better resource management.

*To explore even more technical aspects of this project check out also this article: Data-Centric AI for a Sustainable Water Irrigation System.

Benefits and other Applications of these Methodologies

Applied Methodology 1:

AI model utilizing drones equipped with advanced multispectral and thermal sensors

Can also be utilised in:

Mining and Resource Extraction

  • Benefit: Enhanced environmental monitoring and regulatory compliance.
    • Special Capabilities: Detect subtle environmental changes and temperature anomalies that are invisible to the human eye and traditional CCTV cameras. Real-time monitoring ensures immediate response to potential issues.
    • Application: Utilize drones to monitor land reclamation, detect hidden environmental changes, and ensure strict compliance with environmental regulations. This proactive approach mitigates environmental damage and helps maintain a positive public image, crucial for sustaining operations and investor confidence.

Construction and Infrastructure

  • Benefit: Improved site surveys, progress monitoring, and green infrastructure maintenance.
    • Special Capabilities: Capture high-resolution thermal and multispectral data to identify issues such as heat leaks, water intrusion, and material degradation that are not visible through standard inspections.
    • Application: Conduct comprehensive site surveys with unparalleled detail, monitor construction progress accurately, and maintain green infrastructure efficiently. Detect insulation problems or material fatigue early, preventing costly repairs and ensuring project timelines are met.

Utilities and Energy

  • Benefit: Increased safety and reliability of power distribution.
    • Special Capabilities: Detect thermal hotspots and vegetation encroachment that could lead to power outages or fires, which are often missed by ground inspections and basic surveillance tools.
    • Application: Monitor power lines for potential hazards, inspect renewable energy installations like solar panels and wind turbines for efficiency losses due to undetectable damage, and optimize maintenance schedules. This proactive maintenance prevents outages and enhances operational safety.

Disaster Management and Relief

  • Benefit: Faster and more accurate damage assessment and recovery planning.
    • Special Capabilities: Use thermal imaging to find survivors in debris and multispectral data to assess the extent of vegetation and structural damage that is not visible to the naked eye or conventional cameras.
    • Application: Rapidly deploy drones to disaster zones for immediate and detailed damage assessments. This quick response aids in more efficient allocation of resources and faster recovery times, saving lives and reducing economic losses.

Fisheries and Coastal Management

  • Benefit: Improved monitoring of coastal ecosystems and aquaculture health.
    • Special Capabilities: Detect subtle changes in water quality and coastal vegetation health using thermal and multispectral sensors, identifying problems before they become visible to human observers.
    • Application: Monitor coastal areas for signs of pollution, track erosion rates accurately, and assess the health of marine vegetation. These capabilities ensure sustainable practices and protect marine biodiversity, essential for environmental conservation and regulatory compliance.

Real Estate and Property Management

  • Benefit: Enhanced maintenance of landscaped areas and property value.
    • Special Capabilities: Identify areas of stress in vegetation and structural heat loss with thermal imaging, and assess overall health of landscaping with multispectral data, which are beyond the detection range of traditional methods.
    • Application: Perform precise site assessments, maintain landscapes with targeted interventions, and monitor building envelopes for energy efficiency. This leads to higher property values and increased tenant satisfaction, making properties more attractive and sustainable.

Tourism and Recreation

  • Benefit: Improved aesthetics and maintenance of recreational spaces.
    • Special Capabilities: Monitor turf health and optimize irrigation using data that captures plant health and soil moisture levels invisible to human inspectors and standard cameras.
    • Application: Maintain pristine landscapes in resorts, hotels, and theme parks with minimal water usage and maximal health. Enhance guest experiences by ensuring all recreational areas are in top condition, leading to better reviews and repeat visits.

Manufacturing and Industrial Facilities

  • Benefit: Enhanced maintenance and operational efficiency.
    • Special Capabilities: Detect heat anomalies and equipment malfunctions early with thermal sensors, and monitor structural integrity with multispectral imaging.
    • Application: Conduct regular inspections of manufacturing plants and industrial facilities to detect potential issues before they lead to downtime. Monitor emissions and environmental impact, ensuring compliance with regulations and reducing operational risks.

Smart Cities and Urban Planning

  • Benefit: Improved urban management and sustainability.
    • Special Capabilities: Use multispectral and thermal data to monitor urban heat islands, vegetation health, and infrastructure condition.
    • Application: Implement smart city initiatives by using drones to monitor and manage urban environments. Optimize green spaces, reduce urban heat, and maintain infrastructure efficiently. This data-driven approach supports sustainable urban development and enhances the quality of life for residents.

Further Possibilities

The success of our current model opens up numerous avenues for further enhancements and applications. Potential next steps include:

  • Integrating Real-Time Weather Data: Incorporating current and forecasted weather conditions to dynamically adjust the model’s predictions, improving accuracy in predicting water stress and waterlogging.
  • Expanding to Different Vegetation and Crops: Adapting the model to work with various types of vegetation and crops, making it applicable across multiple agricultural sectors.
  • Developing a Mobile Application: Creating a user-friendly mobile app that provides farmers with real-time insights and recommendations, facilitating precise and timely interventions.
  • Utilizing Advanced Machine Learning Techniques: Implementing deep learning algorithms to further refine the model’s predictive capabilities and accuracy.
  • Leveraging Satellite Data: Combining satellite data with drone data for broader coverage, enhancing the model’s scalability and making it feasible for large-scale agricultural monitoring and management.
  • Automating Irrigation Systems: Integrating with automated irrigation systems to allow for real-time adjustments based on the model’s predictions, optimizing water usage even further.
  • Predicting Maintenance Needs: Developing features that can predict the need for maintenance of irrigation systems and other agricultural equipment, reducing downtime and increasing efficiency.
  • Monitoring Soil Health: Extending the model to include more detailed soil health parameters, providing a comprehensive view of soil fertility and health.

These steps would significantly boost the effectiveness and reach of our solution, driving sustainable agricultural practices on a global scale.

Want to work with us too?

media card
From Seed to Shelf: How These Companies Are Transforming Regenerative Farming in 2024
media card
AI-Driven Sustainability Solutions in a Changing World
media card
Top Water Treatment And Purification Companies To Work With, Across The World
media card
Analyze Pipe-Borne Water Availability in Lagos, Nigeria using Machine Learning