When it comes to forestry management and planning, the more information you have at your fingertips, the better you can get a bird’s-eye view of potential risks, such as climate change, deforestation, general forest degradation and the impacts of forest adjacent communities on forest sustainability. Having this information is the first crucial step. However, sifting through this information and understanding how to use and interpret different pieces of data for actionable outcomes is even more critical.

Decision Support Systems (DSS) are vital to achieving these actionable outcomes and are the ideal resource for forest managers. These computerised tools range from systems that aid in climate comparison, predictions, data visualisation and pest management to tools that anticipate wind damage and tree species suitability and aid in the mapping and managing forested areas.

These systems have become an integral part of forest management and planning that The Food and Agriculture Organization of the United Nations has a Sustainable Forest Management Toolbox that provides software links and case studies specific to Decision Support Systems in forestry.

But what exactly are Decision Support Systems, and how do they help manage forests? Let’s get into the detail.

What are Decision Support Systems (DDS) and how can they help forest managers?

What is a Decision Support System?

If you consider grocery shopping, you’re met with various products and brands you must purchase. Your decisions are based on a range of factors: price, product-need fit, packaging, perhaps the manufacturing company and its legacy, and more subjective criteria like personal preference. As a party of one, you’re using data (some hard and some soft) to make what you consider an informed, best-outcome decision.

Decision Support Systems do the same on a far grander and more sophisticated scale. As a computerised programme, they analyse thousands of data inputs to generate an outcome that helps solve business problems and aid in decision-making on activities that “require judgment, determination, and a sequence of actions, ” says Investopedia and the Corporate Finance Institute. But DSSs don’t just work with data. According to IT and technology magazine CIO, they can also process documents, personal business knowledge, and business models to aid in decision-making. An example of a document-driven DSS might be a company’s searchable report archives. Even Google could be considered a document-driven DSS, spewing out search results based on pre-defined search terms and criteria that aid you in making a decision (whether a research paper or a news article).

The ideal result of using a Decision Support System is decisions that are “more productive, agile, innovative, and reputable”, says the European Journal of Forest Research. It produces these results “by assessing the significance of uncertainties and the tradeoffs involved in making one decision over another,” says CIO. The speed with which it does this as a computerised programme also means quicker decision-making free from too much manual information sifting. These systems have evolved to produce richer, more sophisticated outputs to enhance decision-making quality. Still, even in their earliest form, they were helping everyone from academics to marketers make decisions.

The origin of Decision Support Systems – from the 60s to today

The origin of Decision Support Systems – from the 60s to today

As early as the mid-1960s, computerised quantitative models were being used to help in decision-making and planning, according to A Brief History of Decision Support Systems. Decision Support Systems aided in recurring business planning facilitated production planning, and were instrumental in developing Management Information Systems.

As technology continued to evolve, so did the context in which Decision Support Systems could be used. Traditionally, these systems were developed in academic contexts where access to some of the first time-sharing computer systems was possible.

Technological innovation also brought with it guiding principles that provided an ‘execution framework’ within which DSS could operate, for example, from more standard analytical and financial analysis and modelling to what MIT doctoral student Steven Alter called “optimization models that provide guidelines for action by generating an optimal solution consistent with a series of constraints”. These operations were being performed in the 80s (when Alter was doing his PhD); the sophistication level of Decision Support Systems in a modern context has amplified exponentially.

The 1980s also happened to be when DSS started being used in forestry operations, management and planning. These first systems were “typically hard-coded, and designed to address relatively narrow, well-defined problems…such as pest management for specific pests on specific species,” according to research, but the evolution of technology has broadened the scope of DSS significantly.

One such example is the Huerka Forest DSS in Sweden which showcases the power of DSS through four different software programmes that work seamlessly together to provide rich forest values, data and multi-criteria analytics to support forest planning. Instead of a narrow scope of focus with no room for overlaying of data or overly sophisticated interpretation, Huerka provides insight into “timber and biofuel production, carbon sequestration, dead wood dynamics, habitat for species, recreation and susceptibility to forest damages”, says research from the Swedish University of Agricultural Sciences.

As pressures on forests continue, from climate change to deforestation and encroaching human habitat, Decision Support Systems become more important in predicting risk mitigation and preservation measures, what trends are significant in successful forest planning, what extreme weather and climate events are most likely to have the most significant impact and much more.

Forest Research UK also has a range of free Decision Support Systems to support forest owners and managers in understanding forest impacts and what actions can be taken to increase forest resilience. Some of these systems include ClimateMatch, which compares a site’s future climate to current locations in Europe, and forestGALES, which estimates the probability of wind damage to conifer stands.

Even in the 1980s there was talk of Artificial Intelligence’s role in aiding DSS processes, but as forestry’s problems become more complex and more variables are added to the equation, AI will be at the centre of decision-making. Iris Technology is a company specialising in Intelligent Decision Support Systems, using AI techniques based on Machine Learning and Deep Learning to support businesses’ decision-making activities. Through AI, they can predict anomalies requiring corrective action, predict the biodegradation process of certain biocomposites and coatings in the green chemicals industry, and even integrate patient-specific data into therapies. This is just some of what DSS and AI can do when they come together.

For forestry, AI integrates seamlessly with DSS, harnessing predictive power to make more informed, future-proof decisions. A great example of AI’s role in these Decision Support Systems is a joint forestry project run by the Karlsruhe Institute of Technology and EDI GmbH in Germany. This project uses “a cloud-based decision support system…that uses AI to support local foresters when deciding where to log or when to plant new trees”. All of this is housed on a mobile app.

Putting this kind of decision-making power in the hands of forest managers is fundamental to ensuring sustainable forestry practices and planning.

Forest managers can make better decisions by using Decision Support Systems to handle complex variables

Why do we need decision support systems in forestry?

Forest planning and management is complex due to its sheer scope and the need to consider fauna, flora, water, biodiversity, forest-adjacent communities, carbon sequestration and more. Decision Support Systems allow forest managers to ‘outsource’ this complexity and use the capabilities of computerised programmes to handle thousands of variable, meaningful data points to aid in decision-making.

Most DSS used in forestry are developed “for a specific region and particular environmental, social, economic situation at a specific spatial and temporal scale of interest,” according to Swedish University of Agricultural Sciences researchers. And although this may feel as though it harks back to the more ‘narrow’ functions of earlier Decision Support Systems, this narrowing is mainly geographical and very necessary. A DSS used in Sweden would need to differ in terms of data inputs from one used in South Africa. Tree species, environmental conditions, temperatures, weather patterns, and more all play a vital role in getting the most favourable management and planning outcomes.

In a paper published by the European Journal of Forest Research, the capabilities of nine European DSSs were explored. The assessment of these systems focused on their ability to “generate landscape-level scenarios to explore the output of current and alternative forest management models (FMMs) in terms of a range of [ecosystem services] ESs and the robustness of these FMMs in the face of increased risks and uncertainty.” A forest manager or planner would be left with a forest management model or plan that has considered hundreds of pertinent forestry variables, and they could move forward to implementation with a high degree of confidence. DSSs don’t just remove the guesswork from forestry planning but also expedite the process substantially. Speedy corrective intervention and optimised management approaches are crucial in an industry facing increasing environmental, social, political and legislative pressures.

Although great strides have been made since the 1980s through technological advancement and greater knowledge of system applications, the data availability and quality continue to constrain the efficacy of Decision Support Systems. But, as technology evolves – such as airborne laser scanning – and processes become more refined and automated, DSS will continue to play an imperative role in effective forest management and planning for years.

How we at Swift Geospatial Assist in your decision-making

Through the use of high-quality satellite imagery, GIS and remote sensing, we can provide earth monitoring solutions to clients over a set period of time and for specified monitoring areas, allowing them to see and understand any significant changes. Whether you are monitoring natural or commercial forestry compartments, change detection is facilitated by the latest technology.

Our solutions address overall forest health, as well as forest activities such as harvesting, forest fires, illegal logging and new compartment establishment. We can also provide a general view of the surrounding environment through land cover classifications and mapping as well as encroachment monitoring. Our goal is to provide concise, updated and pertinent information to our clients regardless of what information they need.

Contact us to learn more about how we can enhance your decision-making today!