Vegetation with an adequate supply of water might contribute to cooling the land surface around it through the latent heat flux of transpiration. This study investigates the potential estimation of ...evaporative cooling at plot scale, using soybean as example. Some of the plants’ physiological parameters were monitored and sampled at weekly intervals. A physics-based model was then applied to estimate the irrigation-induced cooling effect within and above the canopy during the middle and late season of the soybean growth period. We then examined the results of the temperature changes at a temporal resolution of ten minutes between every two irrigation rounds. During the middle and late season of growth, the cooling effects caused by evapotranspiration within and above the canopy were, on average, 4.4 K and 2.9 K, respectively. We used quality indicators such as R-squared (R2) and mean absolute error (MAE) to evaluate the performance of the model simulation. The performance of the model in this study was better above the canopy (R2 = 0.98, MAE = 0.3 K) than below (R2 = 0.87, MAE = 0.9 K) due to the predefined thermodynamic condition used to estimate evaporative cooling. Moreover, the study revealed that canopy cooling contributes to mitigating heat stress conditions during the middle and late seasons of crop growth.
•We use a machine-learning model to predict livestock depredation risk by wolves.•The model requires past depredation events and publicly available land use data.•The trained model predicts livestock ...depredation with 74% accuracy.•Thus, landscape context appears to influence livestock depredation.•Results help practitioners on deciding where to carry out protection measures.
Extensive pastoral livestock systems in Central Europe provide multiple ecosystem services and support biodiversity in agricultural landscapes but their viability is challenged by livestock depredation (LD) associated with the recovery of wolf populations. Variation in the spatial distribution of LD depends on a suite of factors, most of which are unavailable at the appropriate scales. To assess if LD patterns can be predicted sufficiently with land use data alone at the scale of one federal state in Germany, we employed a machine-learning-supported resource selection approach. The model used LD monitoring data, and publicly available land use data to describe the landscape configuration at LD and control sites (resolution 4 km * 4 km). We used SHapley Additive exPlanations to assess the importance and effects of landscape configuration and cross-validation to evaluate the model performance. Our model predicted the spatial distribution of LD events with a mean accuracy of 74%. The most influential land use features included grassland, farmland and forest. The risk of livestock depredation was high if these three landscape features co-occurred with a specific proportion. A high share of grassland, combined with a moderate proportion of forest and farmland, increased LD risk. We then used the model to predict the LD risk in five regions; the resulting risk maps showed high congruence with observed LD events. While of correlative nature and lacking specific information on wolf and livestock distribution and husbandry practices, our pragmatic modelling approach can guide spatial prioritisation of damage prevention or mitigation practices to improve livestock-wolf coexistence in agricultural landscapes.
The Asian bush mosquito Aedes japonicus japonicus is an invasive species native to East Asia and has become established in North America and Europe. On both continents, the species has spread over ...wide areas. Since it is a potential vector of human and livestock pathogens, distribution and dissemination maps are urgently needed to implement targeted surveillance and control in case of disease outbreaks. Previous distribution models for Europe and Germany in particular focused on climate data. Until now, effects of other environmental variables such as land use and wind remained unconsidered.
In order to better explain the distribution pattern of Ae. j. japonicus in Germany at a regional level, we have developed a nested approach that allows for the combination of data derived from (i) a climate model based on a machine-learning approach; (ii) a landscape model developed by means of ecological expert knowledge; and (iii) wind speed data. The approach is based on the fuzzy modelling technique that enables to precisely define the interactions between the three factors and additionally considers uncertainties with regard to the acceptance of certain environmental conditions. The model combines different spatial resolutions of data for Germany and achieves a much higher degree of accuracy than previous published distribution models. Our results reveal that a well-suited landscape structure can even facilitate the occurrence of Ae. j. japonicus in a climatically unsuitable region. Vice versa, unsuitable land use types such as agricultural landscapes and coniferous forests reduce the occurrence probability in climatically suitable regions.
The approach has significantly improved existing distribution models of Ae. j. japonicus for the area of Germany. We generated distribution maps with a resolution of 100 × 100 m that can serve as a basis for the design of control measures. All model input data and scripts are open source and freely available, so that the model can easily be applied to other countries or, more generally, to other species.
Visceral leishmaniasis (VL) is re-emerging in Armenia since 1999 with 167 cases recorded until 2019. The objectives of this study were (i) to determine for the first time the genetic diversity and ...population structure of the causative agent of VL in Armenia; (ii) to compare these genotypes with those from most endemic regions worldwide; (iii) to monitor the diversity of vectors in Armenia; (iv) to predict the distribution of the vectors and VL in time and space by ecological niche modeling.
Human samples from different parts of Armenia previously identified by ITS-1-RFLP as L. infantum were studied by Multilocus Microsatellite Typing (MLMT). These data were combined with previously typed L. infantum strains from the main global endemic regions for population structure analysis. Within the 23 Armenian L. infantum strains 22 different genotypes were identified. The combined analysis revealed that all strains belong to the worldwide predominating MON1-population, however most closely related to a subpopulation from Southeastern Europe, Maghreb, Middle East and Central Asia. The three observed Armenian clusters grouped within this subpopulation with strains from Greece/Turkey, and from Central Asia, respectively. Ecological niche modeling based on VL cases and collected proven vectors (P. balcanicus, P. kandelakii) identified Yerevan and districts Lori, Tavush, Syunik, Armavir, Ararat bordering Georgia, Turkey, Iran and Azerbaijan as most suitable for the vectors and with the highest risk for VL transmission. Due to climate change the suitable habitat for VL transmission will expand in future all over Armenia.
Genetic diversity and population structure of the causative agent of VL in Armenia were addressed for the first time. Further genotyping studies should be performed with samples from infected humans, animals and sand flies from all active foci including the neighboring countries to understand transmission cycles, re-emergence, spread, and epidemiology of VL in Armenia and the entire Transcaucasus enabling epidemiological monitoring.
Classification is one of the most widely applied tasks in ecology. Ecologists have to deal with noisy, high-dimensional data that often are non-linear and do not meet the assumptions of conventional ...statistical procedures. To overcome this problem, machine-learning methods have been adopted as ecological classification methods. We compared five machine-learning based classification techniques (classification trees, random forests, artificial neural networks, support vector machines, and automatically induced rule-based fuzzy models) in a biological conservation context. The study case was that of the ocellated turkey (
Meleagris ocellata), a bird endemic to the Yucatan peninsula that has suffered considerable decreases in local abundance and distributional area during the last few decades. On a grid of 10
×
10
km cells that was superimposed to the peninsula we analysed relationships between environmental and social explanatory variables and ocellated turkey abundance changes between 1980 and 2000. Abundance was expressed in three (decrease, no change, and increase) and 14 more detailed abundance change classes, respectively. Modelling performance varied considerably between methods with random forests and classification trees being the most efficient ones as measured by overall classification error and the normalised mutual information index. Artificial neural networks yielded the worst results along with linear discriminant analysis, which was included as a conventional statistical approach. We not only evaluated classification accuracy but also characteristics such as time effort, classifier comprehensibility and method intricacy—aspects that determine the success of a classification technique among ecologists and conservation biologists as well as for the communication with managers and decision makers. We recommend the combined use of classification trees and random forests due to the easy interpretability of classifiers and the high comprehensibility of the method.
Sensitivity analysis (SA) is often applied to evaluate the behavior of ecological models in which the integrated soil and crop processes often vary over time. In this study, the time dependence of ...the parameter sensitivity of a process-based agro-ecosystem model was analyzed for various sites and model outputs. We applied the Morris screening and extended FAST methods by calculating daily sensitivity measures. By analyzing the daily elementary effects using the Morris method, we were able to identify more sensitive parameters compared with the original approach. The temporal extension of the extended FAST method revealed changes in parameter sensitivity during the simulation time. In addition to the dynamic parameter sensitivity, we noticed different relationships between parameter sensitivity and simulation time. The temporal SA performed in this study improves our understanding of the investigated model’s behavior and demonstrates the importance of analyzing the sensitivity of ecological models over the entire simulation time.
Soil samples from several European countries were scanned using medical computer tomography (CT) device and are now available as CT images. The analysis of these samples was carried out using deep ...learning methods. For this purpose, a VGG16 network was trained with the CT images (X). For the annotation (y) a new method for automated annotation, 'surrogate' learning, was introduced. The generated neural networks (NNs) were subjected to a detailed analysis. Among other things, transfer learning was used to check whether the NN can also be trained to other y-values. Visually, the NN was verified using a gradient-based class activation mapping (grad-CAM) algorithm. These analyses showed that the NN was able to generalize, i.e. to capture the spatial structure of the soil sample. Possible applications of the models are discussed.
•We quantified the impact of woody features on land surface temperature in an agricultural area at the regional scale.•The method is applicable wherever the necessary data are available and ...accessible.•Planting additional trees at distances less than 75 m can regulate the land surface temperature of a relatively flat landscape and provide a significant cooling effect to increasing agricultural land's resilience against heat waves.•Eccentricity of woody features influenced land surface temperature significantly with a positive impact on model predictions.
The effects of land cover configuration on land surface temperature (LST) have been extensively documented. However, few studies have examined the effects of woody features and their configuration on LST in agricultural landscapes. A study was conducted in Brandenburg, Germany to examine the potential impacts of small woody features (SWF) on the LST of adjacent agricultural areas. High-resolution maps of woody features at the regional scale, together with the remotely sensed proxies of vegetation conditions (such as topography and crop types), were used to quantify the impact of SWFs on the gradient of LST at different distances during the dry season (June to September) of each year between 2017 and 2020. The structural characteristics of SWFs, orientation, eccentricity and size, were used as input in a multilinear regression model and in machine learning methods to predict LST at different distances. The results of the regression methods applied in this study illustrate that the surface temperature and then the eccentricity of SWFs play the key roles in predicting the gradient of LST at different distances to adjacent fields. This study determines the role of other attributes of SWFs in the prediction of LST, which will influence future landscape planning decisions and strategies.
Display omitted
Forest microclimate can buffer biotic responses to summer heat waves, which are expected to become more extreme under climate warming. Prediction of forest microclimate is limited because ...meteorological observation standards seldom include situations inside forests. We use eXtreme Gradient Boosting ‒ a Machine Learning technique ‒ to predict the microclimate of forest sites in Brandenburg, Germany, using seasonal data comprising weather features. The analysis was amended by applying a SHapley Additive explanation to show the interaction effect of variables and individualised feature attributions. We evaluate model performance in comparison to artificial neural networks, random forest, support vector machine, and multi-linear regression. After implementing a feature selection, an ensemble approach was applied to combine individual models for each forest and improve robustness over a given single prediction model. The resulting model can be applied to translate climate change scenarios into temperatures inside forests to assess temperature-related ecosystem services provided by forests.
•We used XGBoost to predict temperature dynamics inside forests for ecosystem service assessment and the results are compared to those of other machine learning methods such as artificial neural networks (ANN), random forest (RF), support vector machine regression (SVR).•Air temperature, soil temperature, global radiation, and relative humidity provided by meteorological stations are sufficient to reproduce inside-forest temperatures.•We introduced an ensemble method to make the prediction more accurate.•We applied Shapley Additive explanations to interpret the results of the XGBoost model.•XGBoost performed slightly better than other ML methods for estimating forest temperature from weather stations' data.
A new “quick scan” method for an expert-/stakeholder-based impact assessment approach is introduced. This approach aims to reduce the complexity of models, to simulate and visualize the system ...dynamics and to provide a basis for guided discussion with stakeholders. The approach is based on dynamic fuzzy models that can be understood easily and developed by experts and understood and adapted by stakeholders (“white box models”). This open modeling process also forms the basis of the credibility of the simulation results. The quick scan approach is supported by an interactive simulation tool that includes optimization and uncertainty analysis as open source software.
•A new “quick scan” method for an impact assessment approach is introduced.•This approach aims to simulate and visualize the system dynamics.•The approach can be used for a discussion to ensure a sustainable development.•The white box implementation increases the credibility of the model's results.•The implementation is supported by an open source software toolbox.
PDF
