This study focuses on the application of deep learning for transforming semantic point clouds into semantic Building Information Models (BIM) to create a Heritage Digital Twin, centering on Taoping Village, a site of historical and cultural significance in Sichuan, China. Utilizing advanced technologies such as unmanned aerial vehicles and terrestrial laser scanning, we capture detailed point cloud data of the village. A pivotal element of our methodology is the KP-SG neural network, which exhibits outstanding overall performance, particularly excelling in accurately identifying 11 categories. Among those categories, buildings and vegetation, achieves recognition rates of 81% and 83% respectively, and a 2.53% improvement in mIoU compared to KP-FCNN. This accuracy is critical for constructing detailed and accurate semantic BIM models of Taoping Village, facilitating comprehensive architecture and landscape analysis. Additionally, the KP-SG’s superior segmentation capability contributes to the creation of high-fidelity 3D models, enriching virtual reality experiences. We also introduce a digital twin platform that integrates diverse datasets, their semantic information, and visualization tools. This platform is designed to support process automation and decision-making and provide immersive experiences for tourists. Our approach, integrating semantic BIM models and a digital twin platform, marks a significant advancement in preserving and understanding traditional villages like Taoping and demonstrates the transformative potential of deep learning in cultural heritage conservation.

We present TanGeoMS, a tangible geospatial modeling visualization system that couples a laser scanner, projector, and a flexible physical three-dimensional model with a standard geospatial information system (GIS) to create a tangible user interface for terrain data. TanGeoMS projects an image of real-world data onto a physical terrain model. Users can alter the topography of the model by modifying the clay surface or placing additional objects on the surface. The modified model is captured by an overhead laser scanner then imported into a GIS for analysis and simulation of real-world processes. The results are projected back onto the surface of the model providing feedback on the impact of the modifications on terrain parameters and simulated processes. Interaction with a physical model is highly intuitive, allowing users to base initial design decisions on geospatial data, test the impact of these decisions in GIS simulations, and use the feedback to improve their design. We demonstrate the system on three applications: investigating runoff management within a watershed, assessing the impact of storm surge on barrier islands, and exploring landscape rehabilitation in military training areas.

Green walls have been used in built environments as a natural element to bring various benefits, thus improving human health and well-being. However, in conventional virtual environments, the visual connection with a green wall is the only way that this natural element could benefit humans. Unfortunately, the impact of such visual connection on human thermal perception is still not well understood. Thus, we conducted an experimental study with 40 participants comparing the thermal state of two virtual sessions: biophilic (a room with a green wall) and non-biophilic (the same room without a green wall). Both sessions were conducted in a climate chamber under a slightly warm condition (28.89 °C and 50% relative humidity). Participants’ thermal state, skin temperature, and heart rate data were collected. According to the results, participants’ thermal comfort and hand skin temperature were significantly different between the two sessions, and their mean skin temperature was statistically increased over time. The study suggests that before the extent to which the impact of visual stimuli (e.g., green walls) on thermal perception is fully understood, researchers may need to control visual and thermal stimuli separately when using them in immersive virtual environments. Furthermore, the virtual exposure time should be an important consideration when designing experimental procedures.

While nature can benefit people both mentally and physically, contemporary society has become increasingly disconnected from nature. To rebuild a stronger connection with nature in our everyday life, we introduce FloraWear, a do-it-yourself, wearable living interface, that enables people to easily and closely connect with plants. This pictorial introduces how knowledge is built and shared with others using hybrid craft and fabrication, illustrates the material experiments and design development for FloraWear, and discusses how it affects wearers. Then we summarize how FloraWear can help catalyze a shift in people's perspectives towards nature. By developing emotional ties to their wearable plants, FloraWear wearers begin to understand that both they and their plants are part of an ecosystem.

Chemical analyses from 71 watersheds across an ~450 km transect in west-central Panama provide insight into controls on weathering and rates of chemical denudation and CO2 consumption across an igneous arc terrain in the tropics. Stream and river compositions across this region of Panama are generally dilute, having a total dissolved\ud solute value = 118 ± 91 mg/L, with bicarbonate and silica being the predominant dissolved species. Solute, stable isotope, and radiogenic isotope compositions are consistent with dissolution of igneous rocks present in Panama by meteoric precipitation, with geochemical signatures of rivers largely acquired in their upstream regions. Comparison of a headwater basin with its entire watershed\ud observed considerably more runoff production from the high-elevation upstream portion of the catchment than in its much more spatially extensive downstream region. Rock\ud alteration profiles document that weathering proceeds primarily by dissolution of feldspar and pyroxene, with base cations effectively leached in the following sequence: Na > Ca > Mg > K. Control on water chemistry by bedrock lithology is indicated through a linking of elevated ([Na + K]/[Ca + Mg]) ratios in waters to a high proportion of catchment area silicic bedrock and low ratios to mafic bedrock. Sr‑isotope ratios are dominated by basementderived\ud Sr, with only very minor, if any, contribution from other sources. Cation weathering of Ca(sil) + Mg(sil) + Na + K spans about an order in magnitude, from 3 to 32 tons/km2/yr.\ud Strong positive correlations of chemical denudation and CO2 consumption are observed with precipitation, mean watershed elevation, extent of land surface forest cover, and physical\ud erosion rate