top of page

How Are Drones Used in Oil Palm Plantations

Updated: Sep 6, 2019

In Malaysia, oil palm is one of the main economic crop and the larger percentage of the plantations are owned by private individuals categorized as small scale farmers. One of the common activities is taking stock of the number of palm trees within the plantation. This information is vital for estimating yield and productivity. Conventionally, inventorying is achieved by either manually counting oil palm tree crowns on imageries or ground surveying using GPS to gather their location information.

1. Detect unhealthy trees

Health assessment in oil palm plantations is crucial for spotting fungal infection and bacterial disease on the palms. By aerial scanning the plantation using visible RGB camera, NIR, hyperspectral, and multispectral sensors, it is possible to identify temporal and spatial reflectance variations before they can be detected by the naked eyes and associate these changes with palm healths for an early response. Drones equipped with cameras that can detect infected trees enables more targeted treatment instead of mass spraying.

NDVI Cameras

  • Calculate vegetation index describing relative density and health of the palms

  • Healthy vegetation reflects more near-infrared (NIR) and green light compared to other wavelengths.

  • Absorbs more red and blue light.

Thermal Cameras

  • Show heat signature of different spots in the plantation.

  • Track pathogen invasion

  • Hyperspectral Cameras

  • Detection of Ganoderma boninense, causes basal and upper stem rot.

2. Precise Terracing

Drones can also be used for precise terracing, to calculate accurately the volume and estimate the heights of trees. When designing plantation land, farmers want to create terrace.

  • By creating digital elevation models in 3D so that farmers are able to see all the slopes and contours before starting earth works.

  • After modelling, the company will have a tablet equipped with GPS in bulldozers to ease terracing.

  • Up to 5% more trees planted on the hills.

3. Pesticide Spraying Process

Conventional methods for pesticide spraying includes trunk injections, mist blower using trucks and crop dusting using thrush aircraft. Drones and crop dusters do not compete with each other because thrush aircrafts are usually used for huge hectares of land. Compared to the non-aerial method, the use of drones is a lot faster. Pesticide spraying of a hectare of land can be done in 20 minutes which is 100 times faster than trunk injection.

  • Factors reduce crop quality includes crop field not covered properly while spraying.

  • Crop areas overlapping

  • A swarm of UAVs used in a control loop algorithm for agriculture operations.

4. Yield Monitoring

To evaluate the feasibility of having UAVs that can fly over and inside oil palm plantations and collect high resolution detailed photos from different angles for automated creation of yield maps. These maps can tell growers where and when to apply the optimal amount of inputs (i.e., fertilizer, pesticide, water) for creating further sustainability. By using different sensor-based measurement and imaging techniques on each UAV, a real time machine-vision system can be developed for accurate identification of the amount of FFB (fresh fruit bunch) on the palms. In determining instataneous oil palm yield, weight and coordination of FFB on each palm must be known.

  • Weight of FFB estimated using machine vision algorithm that quantifies number of fruits on each palms.

  • Estimated weights georeferenced with coordinates of the corresponding palm using computer programs for creation of database and yield map.

  • Collected data processed by custom-built GIS software for creation of database and yield map.

5. Virtual plantations and Dynamic Web Mapping

One of the limitations on doing research on oil palm plantation is the lack of accurate data and input variables for modeling and simulation purposes. UAV technology can be integrated with image acquisition techniques for 3D reconstruction of the environment and creation of virtual plantations.

  • Created by using range data methods or depth map using laser range finder sensors and 3D scanner instrumentation.

  • An alternative method is image-based reconstruction methods using normal camera and image sensors.

  • UAV equipped with RGB camera collect images of the oil palm plantations from different views and angles.

  • Computer software process these images to create a 3D model, and filter specific wavelength to generate images that corresponds to vegetation index and palm health.

Virtual Plantations created from UAV image data is used to simulate the physical process of palm photosynthesis as a result of different crown sizes and densities intercepting different amount of light radiation. A virtual plantation can be used to estimate palm height, crown size, and inventory database for generating dynamic Web maps and yield prediction models.

These maps identify how different palm height, crown sizes, plantation densities and row orientations in different locations can affect the water and fertilizer demand. Mathematical models are established to estimate nitrogen demand and fertilizer application. Researchers can access to detailed measurements of palm trunk and crown size and the spacing between different palms, leaf area index, and crown density as a preliminary study for the possibility of autonomous variable rate applications and robotic harvesting.

6. Weed detection

The weed pressure algorithm analyzes high resolution drone data to generate a weed pressure map, giving farmers a weed pressure index (ranging from 0-20) along with the percentage of weeds dispersed across the entire survey area. Growers will be able to determine exactly where weeds are more prevalent, thereby allowing them to employ more targeted and strategic management techniques.

7. Soil Analysis

Drones are used to produce 3D maps that can be used to conduct soil analysis on soil property, moisture content and soil erosion. This is very important in planning seed planting patterns. Even after planting, such information is useful for both irrigation and the management of nitrogen level in the soil.

8. Irrigation

Drones equipped with thermal, hyper-spectral or thermal sensors can identify the parts of the field that have become dry. This way the identified areas can be attended to promptly making irrigation precise and timely.

Photo Credit : Tech in Asia


bottom of page