IoT Data Drives Precision Agriculture: Boosting Yields and Cutting Costs

Editor’s note: This article by our global managing editor Rich Quinnell is part of AspenCore Media’s Special Project on 'Agriculture Tech', which examines how IoT, analytics, and sensor technologies are reshaping farming and food production.

While IoT and analytics dominate headlines in industry and infrastructure, agriculture is quietly becoming the next frontier. By integrating sensor networks and real‑time data analytics, farmers can increase yields, reduce losses, and cut operating costs through more precise resource management.

The foundation of precision agriculture is data. Sensors, wireless networking, and sophisticated analytics provide the actionable insights that enable targeted application of fertilizers, water, and pesticides.

Three primary platform categories power this data ecosystem: aerial, ground‑based mobile, and stationary systems. Each platform employs different sensor suites and networking technologies, yet all share a common goal—capturing high‑resolution, actionable data across diverse farm landscapes.

Figure 1 – Multi‑rotor drones are an increasingly popular aerial platform for precision farming of small to mid‑sized fields. (Source: ublox)

Aerial platforms gather data from above using remote sensing. While piloted aircraft and satellites still serve large‑scale surveys, unmanned aerial vehicles (UAVs)—both fixed‑wing and multi‑copter—are rapidly replacing them for mid‑scale operations. Equipped with high‑precision GNSS modules such as the Ublox F9, drones can conduct detailed plant‑health assessments over fields that would otherwise be difficult to monitor.

The key sensor for plant health is a multi‑spectral camera capable of capturing high‑resolution images in visible and near‑infrared (NIR) bands. Most CMOS image sensors exhibit inherent NIR sensitivity, but consumer cameras typically block this range to produce natural‑looking colors. By removing the NIR filter, a CMOS sensor can function as an NDVI camera, as exemplified by the Sentera AGX710.

Figure 2 – Typical color image sensors also include NIR sensitivity, that general‑purpose cameras seek to filter out. (Source: ON Semiconductor)

In plant health monitoring, NIR reflectance is a powerful indicator of vegetation vigor. Healthy leaves reflect more NIR and absorb more red light, leading to the widely used Normalized Difference Vegetation Index (NDVI) = (NIR‑Red)/(NIR+Red). With proper filtering and image processing, a standard CMOS sensor can compute NDVI values, enabling farmers to pinpoint areas that require additional water or fertilizer.

Figure 3 – NDVI surveys provide detailed insight into plant health across whole fields, highlighting where resources like water and fertilizer need more or less application.