<p>Vegetation is a key driver for carbon uptake from the atmosphere to the land. Yet episodes of plant stress and mortality associated with drought and heat waves due to persistent lack of precipitation have been reported over the last decades and are expected to increase under ongoing climate change. It is presumed that climate-related vegetation stress results in progressively worsening plant health and rising mortality. However, the mechanisms driving such mortality are still up for debate because of the complex interconnections between the processes and the factors. Monitoring plant stress and mortality at the ecosystem level remains challenging to quantify since long-term, tree-individual, reliable observations are uncertain. For this reason, here we adapted a satellite-model approach to work on regional forests, before up scaling the results to the global forest.</p> <p>In Belgium, the Wallonia region is covered by 30% forests which are the highest among all the three regions. While with the consecutive recent extreme events especially the droughts and heat waves of 2018, 2019, 2020, and 2022 caused water stress and bark beetle attack. According to the 35 years (1985-2022), land use land cover change extracted by LANDSAT 5,7, and 8 satellites, there is no significant change in forest land in Wallonia, Belgium. Meanwhile, in the current years 2021-2022, there is a decrease in the tree canopy with intensive forest management due to tree plant stress. On the other hand, in Wallonia, the forest is distributed in a significant patch of broadleaves, coniferous leaves, and mixed forest. However, we found that consecutive drought events cause water stress on specific plant species like Norway spruce which are in vulnerable states. For example: in a mixed forest when bark beetle or <em>Scolytinae</em> attacked the spruce tree it is more attracted to the other trees and in this consequence tree species –like  birch and oak –are now also in premature death or deteriorating tree health. In this study, we are using a high spatial resolution (25cm) remote sensing images using Artificial Intelligence and machine learning techniques to find out pixel-based individual plant stress or mortality. In addition, the high-resolution tree mortality extracted data will be used to calibrate CARAIB dynamic vegetation model and analyze the impact of extreme events on trees during the recent past and the future (until 2070). In conclusion, from this study, we plan to improve our model regarding the implementation of plant traits and species mortality aspects towards a better prediction of forest tree species' vulnerability to future extreme weather events.</p>

<p>The use of a dynamic vegetation model, CARAIB, to estimate carbon sequestration from land-use and land-cover change (LULCC) offers a new approach for spatial and temporal details of carbon sink and for terrestrial ecosystem productivity affected by LULCC. Using the remote sensing satellite imagery (Landsat) we explore the role of land use land cover change (LULCC) in modifying the terrestrial carbon sequestration. We have constructed our LULCC data over Wallonia, Belgium, and compared it with the ground-based statistical data. However, the results from the satellite base LULCC are overestimating the forest data due to the single isolated trees. We know forests play an important role in mitigating climate change by capturing and sequestering atmospheric carbon. Overall, the conversion of land and increase in urban land can impact the environment. Moreover, quantitative estimation of the temporal and spatial pattern of carbon storage with the change in land use land cover is critical to estimate. The objective of this study is to estimate the inter-annual variability in carbon sequestration with the change in land use land cover. Here, with the CARAIB dynamic vegetation model, we perform simulations using remote sensing satellite-based LULCC data to analyse the sensitivity of the carbon sequestration. We propose a new method of using satellite and machine learning-based observation to reconstruct historical LULCC. It will quantify the spatial and temporal variability of land-use change during the 1985-2020 periods over Wallonia, Belgium at high resolution. This study will give the space to analyse past information and hence calibrate the dynamic vegetation model to minimize uncertainty in the future projection (until 2070). Further, we will also analyse the change in other climate variables, such as CO<sub>2</sub>, temperature, etc. Overall, this study allows us to understand the effect of changing land-use patterns and to constrain the model with an improved input dataset which minimizes the uncertainty in model estimation.</p>

<p>Changes in land use/land cover (LU/LC) practices are critical to determine and this is one of the crucial driving forces of terrestrial ecosystem productivity and carbon sink variability. However, relatively few studies have quantified the impact of LU/LC change on the terrestrial carbon cycle. In the present study, we developed a workflow for quantifying and assessing changes in terrestrial carbon stocks due to land use change using a dynamic vegetation model. The main objectives are to assess status and variation in carbon stocks across land covers, towards the quantification of spatial distribution and dynamic variation of terrestrial carbon sinks in response to LU/LC change. Here, with the CARAIB dynamic vegetation model, we perform simulations using several sets of LU/LC data to analyse the sensitivity of the carbon sink. We propose a new method of using satellite – and machine learning-based observation to reconstruct historical LU/LC change and compare it with static data from the cadastral map and dynamic data from an agent-based model coupled with CARAIB. It will quantify the spatial and temporal variability of land use during the 2000-2019 period over Belgium at high resolution. This study will give the space to analyse past information and hence calibrate the dynamic vegetation model to minimize uncertainty in the future projection (until 2035). Overall, this study allows us to understand the effect of changing land use pattern and identify the input dataset which minimizes the uncertainty in model estimation.</p>

<p>Pollination is a key ecosystem service vital to the preservation of wild plant communities and good agricultural behaviour. However, pollinators are rapidly declining in Europe, primarily as a result of human activity and climate change. Therefore, there is growing concern that observed declines in insect pollinators may impact on production and revenues from pollinator-dependent crops. In the forest, the presence of pollinators depends strongly on the openness of the canopy and the presence of wild plants that attract pollinators. The distribution of such plants is, therefore, crucial for estimating the pollinators presence. In general, however, there is incomplete knowledge of where those wild plants occur and how well they grow. To overcome this issue, we developed a species distribution model to predict the potential presence of important plant species for pollinators under present and future climatic conditions. The result of the distribution model is then refined using the dynamic vegetation model CARAIB. By combining the results of the distribution model and CARAIB, we can determine where the plants are located and calculate their net primary productivities.</p>