Cultural landscapes are increasingly vulnerable to the compounded effects of potential risks, ecological degradation, and imbalanced heritage value perceptions under intensifying climate change and global urbanization pressures. However, there is a lack of framework that systematically integrates geographical hazards, ecological sensitivity, and both expert and public heritage value perceptions to guide differentiated conservation and development of cultural landscapes. This study proposes a Hazard-Ecology-Perception Landscape Planning (HEPLP) framework to provide a spatially explicit decision-support tool that unifies hazard, ecology, and perception dimensions for cultural landscape planning. HEPLP is evaluated in a case study of Chengde Mountain Resort. A GIS-based methodology is employed to characterize geographical hazards and ecological sensitivity by combining concept of entropy and Analytic Hierarchy Process. Expert scoring and large language model content analysis are used to map heritage value perceptions. Risk-based analysis and three-dimensional clustering revealed nine distinct clusters in cultural landscape, providing spatially grounded evidence for targeted conservation and development strategies. This includes many scenes where previously implemented landscape planning strategies have been designated for complete conservation, as well as clusters where trade-offs between ecological sensitivity and heritage value perception are carefully balanced. Unlike previous frameworks that focused on single or dual dimensions, HEPLP offers an integrative tool for sustainable cultural landscape conservation and development under environmental and social challenges.

ASCAT normalized backscatter (σ₄₀^o) and slope (σ^′) contain valuable information about soil moisture and vegetation. While σ₄₀^o has been assimilated to constrain soil moisture, sometimes together with Leaf Area Index (LAI), this study is the first to assimilate σ^′ directly to constrain vegetation states. Here, we assimilate σ₄₀^o and slope σ^′ into the ISBA-A-gs LSM using the Simplified Extended Kalman Filter (SEKF) using a Deep Neural Network (DNN) as the observation operator. The performances of the data assimilation (DA) and open loop (OL) are evaluated against in-situ soil moisture observations from the International Soil Moisture Network (ISMN), and LAI observations from the Copernicus Global Land Service (CGLS). Given an accurate and physically plausible observation operator, along with well-defined model and observation errors, the data assimilation system should yield improved estimates of the model states. However, results show that the DA performance is neutral compared to the OL in terms of the median unbiased root mean square error (ubRMSE) and Pearson correlation coefficient (ρ) across all validation sites. In addition, an analysis of the residuals and innovations confirms that DA had limited or no impact. This poor performance is perplexing. Furthermore, given the growing interest in the use of machine-learning-based observation operators, it is essential to understand the role that the use of the DNN may be playing in this poor performance. While representativeness errors and error specification play some part, it is demonstrated that the key factor constraining the efficacy of the SEKF is the correct estimation of the Jacobians that control the degree to which the observations update the states in the SEKF. It is argued that the DNN relating model states to satellite observations must have physically-plausible and robust Jacobians for the DNN to be effective in a data assimilation framework.

In the current generation, most land surface models (LSMs) do not explicitly model the plant hydraulic states or fluxes, which limits the ability of LSMs to model evapotranspiration [1], stomatal conductance [2], and monitor and predict drought [3]. Therefore it is necessary to constrain the canopy water dynamics in LSMs. Advanced SCATterometer (ASCAT) provides a long record of C-band backscatter since 2007. A key advantage of the ASCAT instrument is the ability to obtain measurements of the Earth’s surface from different incidence angles. The dependence of ASCAT backscattering coefficient (hereafter referred to as backscatter) on incidence angle provides valuable information about vegetation water dynamics via normalized backscatter (σo 40), and vegetation parameters (slope (σ′), and curvature (σ′′)) of the Taylor expansions of backscatter to incidence angle [4–7]. In this thesis, the ASCAT normalized backscatter and slope are assimilated into the "Interactions between soil, biosphere and atmosphere" (ISBA-A-gs, hereafter referred to as ISBA) LSM.
In order to assimilate ASCAT observables, an observation operator is needed to link between LSM states to radar observations. Radiative transfer models (RTMs) are often used to assimilate radar backscatter into LSM [8, 9]. However, RTMs require moisture content or dielectric properties of soil and vegetation cover which are not simulated by the LSM. Therefore, to directly link land surface states and ASCAT observables, a Deep Neural Network (DNN) was trained and validated in Chapter 3. The performances and sensitivity of theDNNwere evaluated tomake sure the observation operator is physically plausible...

Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification. In this paper, we propose a new dataset, N24News, which is generated from New York Times with 24 categories and contains both text and image information in each news. We use a multitask multimodal method and the experimental results show multimodal news classification performs better than text-only news classification. Depending on the length of the text, the classification accuracy can be increased by up to 8.11%. Our research reveals the relationship between the performance of a multimodal classifier and its sub-classifiers, and also the possible improvements when applying multimodal in news classification. N24News is shown to have great potential to prompt the multimodal news studies.

A Deep Neural Network (DNN) is used to estimate the Advanced Scatterometer (ASCAT) C-band microwave normalized backscatter (σ40o), slope (σ′) and curvature (σ″) over France. The Interactions between Soil, Biosphere and Atmosphere (ISBA) land surface model (LSM) is used to produce land surface variables (LSVs) that are input to the DNN. The DNN is trained to simulate σ40o, σ′ and σ″ from 2007 to 2016. The predictive skill of the DNN is evaluated during an independent validation period from 2017 to 2019. Normalized sensitivity coefficients (NSCs) are computed to study the sensitivity of ASCAT observables to changes in LSVs as a function of time and space. Model performance yields a near-zeros bias in σ40o and σ′. The domain-averaged values of ρ are 0.84 and 0.85 for σ40o and σ′, compared to 0.58 for σ″. The domain-averaged unbiased RMSE is 8.6% of the dynamic range for σ40o and 13% for σ′, with land cover having some impact on model performance. NSC results show that the DNN-based model could reproduce the physical response of ASCAT observables to changes in LSVs. Results indicated that σ40o is sensitive to surface soil moisture and LAI and that these sensitivities vary with time, and are highly dependent on land cover type. The σ′ was shown to be sensitive to LAI, but also to root zone soil moisture due to the dependence of vegetation water content on soil moisture. The DNN could potentially serve as an observation operator in data assimilation to constrain soil and vegetation water dynamics in LSMs.