The COVID-19 pandemic has turned things upside down for the agriculture industry, to say the least. We received plenty of questions from our own customers as well as various ecosystem players concerning the capabilities of our platform and how it enables farmers to work remotely, and I decided to share these thoughts with you in the hopes that you might find them useful now that we are entering a new normalcy and it’s time to start planning for the ramp-up. 

One of the most repetitive inquiries we got was about GIS capabilities, And that’s the reason I decided to focus in this article on the importance and benefits of GIS (Geographical Information Systems) and Remote Sensing, especially in times of crisis.

Aerial footage received from satellites, planes or drones, are not new to the field. Aerial footage by itself, however, is not sufficient: While it does provide an indication of problems in the field, it does not identify their root cause. It must be integrated with other data sources and augmented with additional field data in order to provide the full picture and bring concrete benefits to agribusinesses.

We’ve all experienced (and are still experiencing) the effects of crisis, such as the COVID-19 pandemic. When access to the field is limited, the need for remote field monitoring and control becomes more critical than ever.

GIS enables data collection, spatial analysis performance and new insights on a given plot. This adds a whole new dimension to the collected data and the decision-making process that follows.

In the agriculture ecosystem, spatial information has a significant role and value in simplifying and illustrating the information and data from a plot. It enables the investigation of variation within a plot and cross-referencing of multiple data layers, with the goal of generating new plot-level, farm-level, regional-level or even state-level agronomical insights.

Establishing a strong and valid database is highly important for the farm management team, at all levels – growers and cooperatives alike – and is crucial for making economic decisions on a daily basis, let alone at a time when working remotely is mandatory, as demonstrated by the 3 examples of tools below:

Example #1: Phenological monitoring

Normalized Difference Vegetation Index (NDVI) is one of the most common and efficient indexes for monitoring vegetation. It quantifies vegetation by measuring the difference between near-infrared (which vegetation strongly reflects) and red light (which vegetation absorbs). NDVI ranges from -1 to +1.

The different zones, as demonstrated in these range maps, are based on deviation from NDVI norms within a given plot, with the goal of identifying areas that require special attention. Other data (soil, fertilization, etc.) is then layered on top, to gain an even better understanding of what’s going on.


Example #2: Spatial model

The term spatial modelling refers to a particular form of disaggregation, in which an area is divided into a number (often a large number) of similar units: Typically grid squares or polygons. The model may be linked to a GIS for data input and display. The Agritask platform generates sampling points based on spatial logic and characteristics for the purpose of achieving the highest accuracy possible for the plot data representation. This enables the selection of optimal points for better representation of the spatial characteristics of the plot for each of the different field data collected, in order to support an increase in field yields

The plot is divided into a grid of points. Each point represents the center of an area of 1 hectare. A Sampling pattern can now be deducted based on the plot crop, topography and additional characteristics.

Example #3: Pest and other hazard-related data

Billions of dollars are lost annually by farms around the world due to pests and disease related damages. There are chemical and biological treatments for control of nematodes, but the cost might be prohibitive for field crops – and their efficiency is limited. The Agritask platform provides growers with scouting points for weeds, pests and disease detection, including recommendations for the optimal location and number of points to be inspected, per plot. Alternatively, the distribution of the scouting points can be based on the area/size of the plot, which determines the optimal number and location of the points.

Plant’s parasitic nematodes are an example of a hazard in the field, microscopic worms that feed on the plant’s roots, restrict growth and productivity. From the sampling points, a whole-plot status can be deducted with a spatial analysis, creating a powerful DSS tool that enables decisions and actions to be taken as needed. This addresses the variability of the plot, resulting in high accuracy action and reduction of spraying materials – cost, soil and environmental damages.

To summarize, each of the above mentioned capabilities is available in itself, but the real value can be realized by cross-referencing collected data from different spatial and temporal sources for better, faster decision making.

These tools, combined with a strong, valid database, enable farm management on all levels (growers and cooperatives) a remote control spatial insights, allowing better decision making at any point of the season and is especially crucial in times of crisis, like we all experienced during COVID-19.