Developing kNN forest data imputation for Catalonia

The combined use of LiDAR(Light Detection And Ranging)scanning and field inventories can provide spatially continuous wall-to-wall information on forest characteristics.This information can be used in many ways in forest mapping,scenario analyses,and forest manage-ment planning.This study aimed to find the optimal way to obtain continuous forest data for Catalonia when using kNN imputation(kNN stands for“k nearest neighbors”).In this method,data are imputed to a certain location from k field-measured sample plots,which are the most similar to the location in terms of LiDAR metrics and topographic variables.Weighted multidimensional Euclidean distance was used as the similarity measure.The study tested two different methods to optimize the distance measure.The first method optimized,in the first step,the set of LiDAR and topographic variables used in the measure,as well as the transformations of these variables.The weights of the selected variables were optimized in the second step.The other method optimized the variable set as well as their transformations and weights in one single step.The two-step method that first finds the variables and their transfor-mations and subsequently optimizes their weights resulted in the best imputation results.In the study area,the use of three to five nearest neighbors was recommended.Altitude and latitude turned out to be the most important variables when assessing the similarity of two locations of Catalan forests in the context of kNN data imputation.The optimal distance measure always included both LiDAR metrics and topographic variables.The study showed that the optimal similarity measure may be different for different regions.Therefore,it was suggested that kNN data imputation should always be started with the optimization of the measure that is used to select the k nearest neighbors.

Forest use suitability:Towards decision-making-oriented sustainable management of forest ecosystem services

Management of forest lands considering multi-functional approaches is the basis to sustain or enhance the provi-sion of specific benefits,while minimizing negative impacts to the environment.Defining a desired management itinerary to a forest depends on a variety of factors,including the forest type,its ecological characteristics,and the social and economic needs of local communities.A strategic assessment of the forest use suitability(FUS)(namely productive,protective,conservation-oriented,social and multi-functional)at regional level,based on the provision of forest ecosystem services and trade-offs between FUS alternatives,can be used to develop management strategies that are tailored to the specific needs and conditions of the forest.The present study assesses the provision of multiple forest ecosystem services and employs a decision model to identify the FUS that sup-ports the most present and productive ecosystem services in each stand in Catalonia.For this purpose,we apply the latest version of the Ecosystem Management Decision Support(EMDS)system,a spatially oriented decision support system that provides accurate results for multi-criteria management.We evaluate 32 metrics and 12 as-sociated ecosystem services indicators to represent the spatial reality of the region.According to the results,the dominant primary use suitability is social,followed by protective and productive.Nevertheless,final assignment of uses is not straightforward and requires an exhaustive analysis of trade-offs between all alternative options,in many cases identifying flexible outcomes,and increasing the representativeness of multi-functional use.The assignment of forest use suitability aims to significantly improve the definition of the most adequate management strategy to be applied.

Performance of statistical and machine learning-based methods for predicting biogeographical patterns of fungal productivity in forest ecosystems

Background:The prediction of biogeographical patterns from a large number of driving factors with complex interactions,correlations and non-linear dependences require advanced analytical methods and modeling tools.This study compares different statistical and machine learning-based models for predicting fungal productivity biogeographical patterns as a case study for the thorough assessment of the performance of alternative modeling approaches to provide accurate and ecologically-consistent predictions.Methods:We evaluated and compared the performance of two statistical modeling techniques,namely,generalized linear mixed models and geographically weighted regression,and four techniques based on different machine learning algorithms,namely,random forest,extreme gradient boosting,support vector machine and artificial neural network to predict fungal productivity.Model evaluation was conducted using a systematic methodology combining random,spatial and environmental blocking together with the assessment of the ecological consistency of spatially-explicit model predictions according to scientific knowledge.Results:Fungal productivity predictions were sensitive to the modeling approach and the number of predictors used.Moreover,the importance assigned to different predictors varied between machine learning modeling approaches.Decision tree-based models increased prediction accuracy by more than 10%compared to other machine learning approaches,and by more than 20%compared to statistical models,and resulted in higher ecological consistence of the predicted biogeographical patterns of fungal productivity.Conclusions:Decision tree-based models were the best approach for prediction both in sampling-like environments as well as in extrapolation beyond the spatial and climatic range of the modeling data.In this study,we show that proper variable selection is crucial to create robust models for extrapolation in biophysically differentiated areas.This allows for reducing the dimensions of the ecosystem space described by the predictors of the models,resulting in higher similarity between the modeling data and the environmental conditions over the whole study area.When dealing with spatial-temporal data in the analysis of biogeographical patterns,environmental blocking is postulated as a highly informative technique to be used in cross-validation to assess the prediction error over larger scales.