Estimating soil moisture content under grassland with hyperspectral data using radiative transfer modelling and machine learning.

The monitoring of soil moisture content (SMC) at very high spatial resolution (<10m) using unmanned aerial systems (UAS) is of high interest for precision agriculture and the validation of large scale SMC products. Data-driven approaches are the most common method to retrieve SMC with UAS-borne data at water limited sites over non-disturbed agricultural crops. A major disadvantage of data-driven algorithms is the limited transferability in space and time and the need of a high number of ground reference samples. Physically-based approaches are less dependent on the amount of samples and are transferable in space and time. This study explores the potential of (1) a hybrid method targeting the soil brightness factor of the PROSAIL model using a variational heteroscedastic Gaussian Processes regression (VHGPR) algorithm, and (2) a data-driven method employing VHGPR for the retrieval of SMC over three grassland sites based on UAS-borne VIS-NIR (399-1001 nm) hyperspectral data. The sites were managed by mowing (Fendt), grazing (Grosses Bruch) and irrigation (Marquardt). With these distinct local pre-conditions we aimed to identify factors that favor and limit the retrieval of SMC. The hybrid approach presented encouraging results in Marquardt (RMSE = 1.5 Vol_%, R2 = 0.2). At the permanent grassland sites (Fendt, Grosses Bruch) the thatch layer jeopardized the application of the hybrid model. We identified the complex canopy structure of grassland as the main factor impacting the hybrid SMC retrieval. The data-driven approach showed high accuracy for Fendt (R2 = 0.84, RMSE = 8.66) and Marquardt (R2 = 0.4, RMSE = 10.52). All data-driven models build on the LAI-SMC relationship. However, this relationship was hampered by mowing (Fendt), leading to a lack of transferability in time. The alteration of plant traits by grazing prevents finding a relationship with SMC in Grosses Bruch. In Marquardt, we identified the timelag between changes in SMC and plant response as the main reason of decrease in model accuracy. Yet, the model performance is accurate in undisturbed and water-limited areas (Marquardt). The analysis points to challenges that need to be tackled in future research and opens the discussion for the development of robust models to retrieve high resolution SMC from UAS-borne remote sensing observations.

Spatio-temporal feature attribution of European summer wildfires with Explainable Artificial Intelligence (XAI).

Wildfires are among the most destructive natural disasters globally. Understanding the drivers behind wildfires is a crucial aspect of preventing and managing them. Machine learning methods have gained popularity in wildfire modeling in recent years, but their algorithms are usually complex and challenging to interpret. In this study, we employed the SHapley Additive exPlanations (SHAP) value, an Explainable Artificial Intelligence method, to interpret the model and thus generate spatio-temporal feature attributions. Our research focuses on the forest, shrub and herbaceous vegetated areas of Europe during the summers from 2018 to 2022. Using burned areas, meteorology, vegetation, topography, and anthropogenic activity data, we established a wildfire occurrence model using random forest classification. The model was highly accurate, with an Area Under the Receiver Operating Characteristic Curve of 0.940. The SHAP results revealed six features that significantly influence wildfire occurrences: land surface temperature (LST), solar radiation (SR), Temperature Condition Index (TCI), Normalized Difference Vegetation Index (NDVI), precipitation (Prep), and soil moisture (SM). The tipping points for the positive or negative shifts in contributions are around 30 °C (LST), 2.20e7 J/m^2 (SR), 0.2 (TCI), 0.78 (NDVI), 2 mm/h (Prep), and 0.18 (SM). These predictors display strong spatial variability in their contribution levels. In Southern Europe, LST and SR emerge as the primary contributors to wildfires, making substantial impacts. Conversely, in regions at mid and high latitudes in Europe, NDVI, Prep, and SM assume a more prominent role in promoting wildfires, albeit with relatively smaller contributions. Furthermore, the disparities in SHAP values for TCI and SMCI across different years provide valuable insights into the effects of variation in regional meteorological conditions on wildfires. Our study provides a new approach to uncovering the spatio-temporal variations of feature contributions, which will help to better understand the mechanism of wildfire occurrence and enhance prevention and mitigation.

Modeling urban evapotranspiration using remote sensing, flux footprints, and artificial intelligence.

As climate change progresses, urban areas are increasingly affected by water scarcity and the urban heat island effect. Evapotranspiration (ET) is a crucial component of urban greening initiatives of cities worldwide aimed at mitigating these issues. However, ET estimation methods in urban areas have so far been limited. An expanding number of flux towers in urban environments provide the opportunity to directly measure ET by the eddy covariance method. In this study, we present a novel approach to model urban ET by combining flux footprint modeling, remote sensing and geographic information system (GIS) data, and deep learning and machine learning techniques. This approach facilitates spatio-temporal extrapolation of ET at a half-hourly resolution; we tested this approach with a two-year dataset from two flux towers in Berlin, Germany. The benefit of integrating remote sensing and GIS data into models was investigated by testing four predictor scenarios. Two algorithms (1D convolutional neural networks (CNNs) and random forest (RF)) were compared. The best-performing models were then used to model ET values for the year 2019. The inclusion of GIS data extracted using flux footprints enhanced the predictive accuracy of models, particularly when meteorological data was more limited. The best-performing scenario (meteorological and GIS data) showed an RMSE of 0.0239 mm/h and R2 of 0.840 with RF and an RMSE of 0.0250 mm/h and a R2 of 0.824 with 1D CNN for the more vegetated site. The 2019 ET sum was substantially higher at the site surrounded by more urban greenery (366 mm) than at the inner-city site (223 mm), demonstrating the substantial influence of vegetation on the urban water cycle. The proposed method is highly promising for modeling ET in a heterogeneous urban environment and can support climate change mitigation initiatives of urban areas worldwide.

Heat waves and urban heat islands in Europe: A review of relevant drivers.

The climate change and the proceeding urbanization create future health challenges. Consequently, more people around the globe will be impaired by extreme weather events, such as heat waves. This study investigates the causes for the emergence of surface urban heat islands and its change during heat waves in 70 European cities. A newly created climate class indicator, a set of meaningful landscape metrics, and two population-related parameters were applied to describe the Surface Urban Heat Island Magnitude (SUHIM) - the mean temperature increase within the urban heat island compared to its surrounding, as well as the Heat Magnitude (HM) - the extra heat load added to the average summer SUHIM during heat waves. We evaluated the relevance of varying urban parameters within linear models. The exemplary European-wide heat wave in July 2006 was chosen and compared to the average summer conditions using MODIS land surface temperature with an improved spatial resolution of 250m. The results revealed that the initial size of the urban heat island had significant influence on SUHIM. For the explanation of HM the size of the heat island, the regional climate and the share of central urban green spaces showed to be critical. Interestingly, cities of cooler climates and cities with higher shares of urban green spaces were more affected by additional heat during heat waves. Accordingly, cooler northern European cities seem to be more vulnerable to heat waves, whereas southern European cities appear to be better adapted. Within the ascertained population and climate clusters more detailed explanations were found. Our findings improve the understanding of the urban heat island effect across European cities and its behavior under heat waves. Also, they provide some indications for urban planners on case-specific adaptation strategies to adverse urban heat caused by heat waves.

Facilitating political decisions using species distribution models to assess restoration measures in heavily modified estuaries.

The European Water Framework Directive requires a good ecological potential for heavily modified water bodies. This standard has not been reached for most large estuaries by 2015. Management plans for estuaries fall short in linking implementations between restoration measures and underlying spatial analyses. The distribution of emergent macrophytes - as an indicator of habitat quality - is here used to assess the ecological potential. Emergent macrophytes are capable of settling on gentle tidal flats where hydrodynamic stress is comparatively low. Analyzing their habitats based on spatial data, we set up species distribution models with 'elevation relative to mean high water', 'mean bank slope', and 'length of bottom friction' from shallow water up to the vegetation belt as key predictors representing hydrodynamic stress. Effects of restoration scenarios on habitats were assessed applying these models. Our findings endorse species distribution models as crucial spatial planning tools for implementing restoration measures in modified estuaries.

Estimating greenhouse gas emissions of European cities--modeling emissions with only one spatial and one socioeconomic variable.

Substantive and concerted action is needed to mitigate climate change. However, international negotiations struggle to adopt ambitious legislation and to anticipate more climate-friendly developments. Thus, stronger actions are needed from other players. Cities, being greenhouse gas emission centers, play a key role in promoting the climate change mitigation movement by becoming hubs for smart and low-carbon lifestyles. In this context, a stronger linkage between greenhouse gas emissions and urban development and policy-making seems promising. Therefore, simple approaches are needed to objectively identify crucial emission drivers for deriving appropriate emission reduction strategies. In analyzing 44 European cities, the authors investigate possible socioeconomic and spatial determinants of urban greenhouse gas emissions. Multiple statistical analyses reveal that the average household size and the edge density of discontinuous dense urban fabric explain up to 86% of the total variance of greenhouse gas emissions of EU cities (when controlled for varying electricity carbon intensities). Finally, based on these findings, a multiple regression model is presented to determine greenhouse gas emissions. It is independently evaluated with ten further EU cities. The reliance on only two indicators shows that the model can be easily applied in addressing important greenhouse gas emission sources of European urbanites, when varying power generations are considered. This knowledge can help cities develop adequate climate change mitigation strategies and promote respective policies on the EU or the regional level. The results can further be used to derive first estimates of urban greenhouse gas emissions, if no other analyses are available.