A novel decision support system for designing and assessing phytoremediation‐to‐biofuel value chains

Abstract The design of biofuel value chains is a complex process due to the large number of stakeholders involved, seasonality in feedstock availability, security of supply, logistics costs, efficiency considerations, and its multi‐node nature. Decisions on designing phytoremediation‐to‐biofuel value chains are even more complicated, due to the involvement of additional stakeholders, contamination impacting the types of biomass that can be grown and its yield, sparse land availability or small land plots – leading to lack of efficiency and economies of scale – and higher technology costs due to the need for contaminant separation. This paper presents a decision support system (DSS) that supports biofuel value chains design when the biomass originates from the phytoremediation of contaminated land. It integrates various tools, including geographic information system (GIS) data input, machine learning for biomass suitability assessment, supply chain optimization, evaluation of economic, environmental, and social key performance indicators, and a multicriteria method for ranking scenarios (i.e. combinations of biomass types and conversion technologies). The aim is to assist various types of stakeholders to assess the feasibility of establishing a phytoremediation‐to‐biofuel value chain, to decontaminate land, and to produce clean biofuels, while simultaneously considering multiple environmental, social, and economic criteria. A case‐study application in Greece is also presented and the findings are discussed. The web‐based DSS tool has several novel aspects, such as its ability to allow end‐to‐end value‐chain assessment, the adoption of novel machine learning methods to predict biomass species performance on contaminated land and to allow consideration of mobile pyrolysis conversion units together with fixed conversion units.