A method that produces a plausible result has not automatically demonstrated that it works for its intended users. Validation requires a defined question, suitable reference evidence, and an evaluation design that reflects how the method will be used. This perspective examines which observations should be compared, how they should be sampled, and which errors matter in practice. It also considers the difference between evidence used to develop a method and evidence reserved for evaluating it. The objective is a test that can reveal weaknesses as well as confirm useful performance.
This working guide considers viewing geometry and brdf effects along river water corridors. The immediate decision is to prioritise river reaches for sampling. Useful reference evidence includes sampling time, river stage and reach-specific water observations. The case is an illustrative planning context, with assumptions to check against the actual sensor, landscape and project requirements.
The setting: River water corridors
A river corridor can vary quickly in width, bank exposure, flow conditions and the surrounding land cover. A remotely observed reach may include water, sediment, vegetation and structures within the same footprint. Define the monitoring question before choosing an interpretation scale. Mapping the position of visible water, investigating a colour change and estimating a particular water-quality variable are different tasks, even where they draw on the same acquisition.
Spatial resolution and geometric alignment are critical for narrow reaches. A small offset can change how much bank or vegetation contributes to a measurement. Cloud, shadow, surface reflection and adjacency effects can further complicate optical interpretation. Compare suitable acquisitions and retain the exact dates supporting each reach summary. Where river conditions change rapidly, consider whether the available observation frequency is sufficient for the decision the service is intended to support.
Field sampling should identify the sampled reach, location and collection time, together with river conditions that affect comparability. A single bank-side sample may not describe the full width or a downstream reach observed at another time. A spectral anomaly can help select an investigation site without establishing its cause. More specific claims require a validated relationship with representative measurements, while a transparent water and reach inventory can already make a sampling programme more systematic.
The observed surface has a direction-dependent response
A surface does not necessarily reflect incoming light equally in every direction. Its measured brightness can change as the positions of the Sun, surface and sensor change, even when the surface itself is similar. The bidirectional reflectance distribution function provides a framework for describing this directional behaviour. In practical image analysis, the relevant lesson is that a difference between observations may contain a geometry effect as well as a real surface change. Canopy structure, shadows and surface roughness can all influence that relationship.
The magnitude and pattern of a geometry effect depend on the landscape and spectral measurement. A row crop, closed forest and exposed soil need not behave in the same way. Terrain introduces another layer because slope and aspect alter local illumination. A simple brightness adjustment is not automatically an adequate solution. A workflow should first identify the type of comparison it needs and whether the available product already includes a relevant normalisation. Applying an additional correction without understanding prior processing can create a new inconsistency.
Normalise geometry with a clear purpose
Geometry normalisation uses a model or adjustment to express observations under a more consistent reference condition. It is an approximation designed for a defined purpose, and its performance should be checked rather than assumed. Keep the input geometry, model assumptions and processing version where they are available. Compare representative surfaces before and after the adjustment. A useful test examines whether the correction reduces systematic variation in stable areas while preserving changes that are supported independently by management records or field observations.
For an agricultural service, the importance of this effect depends on the size of the change being interpreted. A subtle trend can be more sensitive to residual geometry variation than a major harvest event. Evaluate whether an apparent improvement in a time series survives across seasons and fields, including those with different canopy arrangements. Retain a clear explanation of what has been normalised and what remains uncertain. Viewing geometry becomes manageable when it is treated as part of the measurement context instead of being attributed silently to crop condition or land-cover change.
Use observation labels with consistent meanings
A reference label should describe an observation that another person could recognise or reproduce. Broad terms such as good, damaged, or unusual can conceal substantial differences between collection teams. Begin by defining the feature or condition being recorded, the observation unit, and the evidence needed to assign a label. Where possible, distinguish a direct measurement from an interpretation made by the observer.
Provide a short collection guide with examples, boundary cases, and a way to record uncertainty. Train observers using shared cases before relying on independently collected labels. If two observers disagree, preserve the disagreement long enough to understand its cause. It may reveal an unclear definition, a genuinely ambiguous condition, a difference in observation scale, or a problem in matching the reference record to the remote measurement.
Retain the context that makes the label interpretable. Location, time, collection method, observer role, and relevant surface conditions can be essential for later review. Changes to the label scheme should be documented and related to earlier versions where a defensible correspondence exists. Consistent labels do not eliminate uncertainty, but they make it possible to investigate disagreement, evaluate analytical methods, and identify where better definitions or additional measurements would improve the evidence.
Design an evaluation that reflects deployment
A model evaluation should resemble the conditions in which the model will be used. Start by identifying which relationships the development data share: nearby locations, repeated observations of the same unit, common collection teams, or measurements from a single period. These relationships can make records less independent than they appear. An evaluation that ignores them may test the ability to recognise familiar conditions rather than the ability to operate in a new setting.
Choose a split strategy that matches the intended transfer. Holding out locations, seasons, operational units, or acquisition conditions can answer different questions. Document which question each split is designed to address, and keep the held-out evidence separate while selecting features and tuning the method. Repeatedly inspecting the same evaluation set to improve a model gradually makes that set part of development, even if it retains its original label.
Report results at a scale that is meaningful to the user. A strong average can hide poor performance for important subgroups or unusual conditions. Examine error patterns and retain examples of both successful and unsuccessful predictions. Where the evidence covers only a limited range of conditions, describe that range explicitly. The evaluation then becomes a practical guide to suitable use, further testing, and the collection of additional reference observations.
Bring the evidence back to the decision
The validation record should explain the population represented by the test, the reference observations used, and the limitations of the comparison. Report meaningful errors alongside useful successes, and retain examples that challenge the method. Treat wider deployment as a new opportunity to evaluate transfer across relevant conditions. A well-designed validation programme gives users a defensible basis for deciding where the method is useful, where additional evidence is needed, and where another approach may be appropriate.
Sources & further reading
Explore the bhumisat spacecraft concept and our vision towards 2030, or return to the journal.



