23 Decision support
Decision Support is not a passive end-stage where algorithms dictate what to do.
A proper DSS is:
-
Transparent: every step, assumption and transformation is explicit
-
Interpretive: the user understands why a given recommendation emerges
-
Adaptive: models respond to the specificity of a farm, a territory, a context
-
Interactive: human judgment is not replaced but amplified
- Accountable: decisions are traceable, explainable and ethically grounded
In this course, when we design spatial layers, build models, and test scenarios, we are learning the foundations of responsible decision support. Coding is the instrument; judgment is the purpose.
23.1 Decision Support Principles
- Decision-making must integrate human interpretation with algorithmic output.
- A DSS must support uncertainty analysis, scenario comparison, and sensitivity evaluation.
- Geospatial DSS tools should explicitly connect data, models, and decisions through reproducible workflows.
- Effective decision support requires aligning technical outputs with practical constraints and stakeholder needs.
- A DSS is only as strong as the assumptions behind it: transparency is non-negotiable.
23.2 Why \(C^3\) Matters in Digital Mapping, Geospatial Statistics & Decision Support
Recently, an important debate has emerged in Europe about how universities should respond to the rapid expansion of artificial intelligence and automated knowledge systems. A central argument invokes the \(C^3\) triad:
- Critical thinking
- Contrarian thinking
- Creativity
These three capabilities are not optional extras. They are exactly what will distinguish future professionals who guide digital transformation from those who are merely shaped by it.
In the course on Digital Mapping, Geospatial Statistics & Decision Support, we work together on producing information that does not yet exist – through code, models, simulations and spatial analytics. Every map you build, every model you implement, every script you write is not just a technical task: it is a decision-making act. You choose what to represent, how to structure data, how to validate models, and what assumptions matter.
This process requires more than technical skills. It requires the capacity to question defaults, to resist cognitive conformism, and to take responsibility for methodological choices.
This is precisely where \(C^3\) becomes essential.
23.2.1 Critical thinking
Interrogate data sources, modeling assumptions, algorithmic outcomes.
In geospatial work, blind acceptance of outputs is dangerous. Every interpolated surface, every predictive model, every digital map is a hypothesis, not a truth. Critical thinking is the safeguard that keeps science honest and decision support reliable.
23.2.2 Contrarian thinking
Dare to question the “standard way” when the context demands it.
Decision Support Systems in agriculture – and especially in Precision Livestock Farming – must deal with incomplete data, ambiguous situations, and complex behaviours. Innovation emerges when someone asks, “What if the usual method is not good enough here?” (link to the what-if modelling of decision support systems). Contrarian thinking means challenging norms productively for the sake of improvement.
23.2.3 Creativity
The future will belong to those who can build new data, not only interpret existing ones.
When we design new geospatial indicators, simulate missing data, or integrate sensor signals with statistical models, we are inventing the raw material from which decisions will be made. Creativity enables you to design new solutions, new pipelines, new trajectories, new ways to see the territory and the animals we manage.
23.3 Final message
Technologies will continue to advance – AI, automation, cloud infrastructures such as GCI3 and CPS4, digital twins. But no machine can substitute what genuinely defines you as future professionals:
your ability to think critically, to challenge intelligently, and to create boldly.
The weeks of work in our course are not just an academic exercise.
They are training for you to take part in the decisions that will shape the future of agriculture and livestock management, without falling into cognitive conformism or passive dependence on algorithmic outputs.