Area Monitoring — Expert Judgement Application

Helping experts with decision making where machine learning struggles

Matjaz Stanfel
Sentinel Hub Blog


Expert app — used for deciding about “yellow parcels”, designated by Traffic Light System, and also for marker validation and identification of specific ground conditions.

This is a multi-part series about machine learning and EO data supporting Common Agriculture Policy. Find information about related blog posts at the bottom.

When wrong results have financial consequences

In Area Monitoring (AM) having “better than 90% accuracy” ML results could still mean that 10% of the farmers might be wrongly penalized or that the Member State has to return the funds distributed inappropriately. Both outcomes result in millions of EURs of unnecessary cost and unhappy claimants.

The Expert Judgement Application (also known as the Expert App) is an integral part of AM, used by authorized operators to decide about parcels, where compliance (or non-compliance) cannot be determined automatically with an appropriate level of confidence— yellow parcels based on traffic lights (TL) nomenclature.

Assessment of yellow TL with the Expert-App. The configurable User Interface consists of the time-lapse component [1] used for fast and convenient visualization of changes through the year, different marker histograms [2] (ie. similarity, distance...) or a table with FOI attributes, [3] tabs for displaying results of markers, scenario and a map [4] with useful layers (especially VHR imagery), a signal/vegetation index profile [5] which indicates continuous index values as well as automatically detected events and observations, utility toolbar [6] for a definition of parameters used for the visualization, a list of tasks [7] which should be performed within the package and finally, buttons for TL assessment [8].

Besides categorisation of the yellow TL, the Expert-App is also used in the effective marker development procedure, for validation of automatically generated markers and, feeding the results back to the ML model for further improvements, hopefully resulting in more reliable red/green categorisations, in a positive reinforcing feedback loop.

As an example, expert validation is made by confirming or rejecting automatically derived crop group and/or land cover, or in case of event markers, by selecting image chips on which event can be recognized (as illustrated in the figure below).

Validation of automatically-detected mowing events by selecting/de-selecting image chips where removal of vegetation (mowing) is clearly observed. The efficient Expert-App enables marker validation to be completed in just a matter of seconds.

The process also facilitates the identification of other clearly visible features, thereby further improving the reliability of the ML model used for the automatic assessment, as shown in the figure below.

Definitive identification of bare soil is made by “selecting” image chips where bare soil is clearly evident. The task is completed by clicking the “confirm” button.

Organizing and distributing work

However advanced the ML model is, it will struggle to provide a satisfactory degree of confidence for small or narrow parcels, or in areas with multiple cropping, partial abandonments and other mixed-signal responses. Thousands of parcels will require operators engagement to make a decision on whether the agricultural parcel is compliant with the CAP policy or not.

The workflow part of the Expert-App serves to distribute and organize the work, starting with the bulk creation of package bundles, each consisting of relevant (and, often, related) tasks to be performed, then assigned to the authorised users.

Package bundles are generated through the wizard - and after selecting the module type (e.g. TL assessment, marker validation, or clear-event identification), and desired inference (an application of the model on the data to produce a marker), authorised users may filter FOI’s based on available parameters (such as crop type, land use, area, etc.) or markers, in order to select priority packages of interest.

Wizard for creation of package bundles. FOI filtering is carried out based on the data retrieved from the services. In this example, the process of creating a package bundle for wheat fields larger than 0,1ha is illustrated.


The expert app consists of several components, namely;

  • Admin module, used for the creation of package bundles and package distribution among users and
  • Main UI, where all available data is provided for expert’s interpretation (image chips, time-lapse, FOI’s attribute data, map with various layers such as aerial imagery and VHR satellite imagery, signal graph/profile, task list, and the settings panel for adapting the view).
Scenario flow informs experts about the reason why a specific FOI is marked with “yellow” status.

It should be noted that visual components (time-lapse and signal graph/profiles) are standalone components provided as generic web services, which can be integrated into any other application.

Visual components (signal graph and timelapse) are prepared as standalone components.

Commissioning higher-resolution imagery

The main source of imagery is from Sentinel, whose excellent availability and revisit capability is suitable for most agricultural parcels, but where parcel size or shape (e.g. narrow elongated parcels only a few meters wide) become an issue, the Expert-App permits the integration of specially-commissioned data from various high-resolution satellite imagery (e.g. PlanetScope, SPOT, Pleiades) to assist in the decision making.

the Expert-App interface allows the user to order VHR imagery of higher spatial resolution from the relevant supplier services, defining desired source, date, and filtered on parameters such as cloud coverage. In a matter of minutes, users could make a validation by showing the results in the Expert App map.

For small parcels (FOI size in this example is 7.5x13m) where there is no Sentinel data assessment could be done by analyzing available or specially-ordered VHR imagery.

Stay tuned — further developments of the Expert-App to come

ML-assisted rapid processing of large amounts of Earth Observation data will provide timely and effective area monitoring for many applications, and the Expert-App will provide additional support where there is still some ambiguity. As the system goes into production dealing with real-life cases, we are continuing to evolve and refine it.

Soon you may expect other posts related to the expert app in which we will dive deeper into the subject and present components in more detail, as well as show few real-life examples from Slovenia followed by explanations of how decision making is improved. Stay tuned!

Check the Area Monitoring documentation for more information.

Further reading

This post is one of the series of blogs related to our work in Area Monitoring. We have decided to openly share our knowledge on this subject as we believe that discussion and comparison of approaches are required among all the groups involved in it. We would welcome any kind of feedback, ideas and lessons learned. For those willing to do it publicly, we are happy to host them at this place.

The content: