Search for: All records

Accurate prediction of citywide crowd activity levels (CALs),i.e., the numbers of participants of citywide crowd activities under different venue categories at certain time and locations, is essential for the city management, the personal service applications, and the entrepreneurs in commercial strategic planning. Existing studies have not thoroughly taken into account the complex spatial and temporal interactions among different categories of CALs and their extreme occurrences, leading to lowered adaptivity and accuracy of their models. To address above concerns, we have proposedIE-CALP, a novel spatio-temporalInteractive attention-based andExtreme-aware model forCrowdActivityLevelPrediction. The tasks ofIE-CALPconsist of(a)forecasting the spatial distributions of various CALs at different city regions (spatial CALs), and(b)predicting the number of participants per category of the CALs (categorical CALs). To realize above, we have designed a novel spatial CAL-POI interaction-attentive learning component inIE-CALPto model the spatial interactions across different CAL categories, as well as those among the spatial urban regions and CALs. In addition,IE-CALPincorporate the multi-level trends (e.g., daily and weekly levels of temporal granularity) of CALs through a multi-level temporal feature learning component. Furthermore, to enhance the model adaptivity to extreme CALs (e.g., during extreme urban events or weather conditions), we further take into account theextreme value theoryand model the impacts of historical CALs upon the occurrences of extreme CALs. Extensive experiments upon a total of 738,715 CAL records and 246,660 POIs in New York City (NYC), Los Angeles (LA), and Tokyo have further validated the accuracy, adaptivity, and effectiveness ofIE-CALP’s interaction-attentive and extreme-aware CAL predictions.

 

Most land plants alternate between generations of sexual gametophytes and asexual sporophytes. Unlike seed plants, fern gametophytes are free-living and grow independently of their sporophytes. In homosporous ferns like Ceratopteris, gametophytes derived from genetically identical spores exhibit sexual dimorphism, developing as either males or hermaphrodites. Males lack meristems and promote cell differentiation into sperm-producing antheridia. In contrast, hermaphrodites initiate multicellular meristems that stay undifferentiated, sustain cell division and prothallus expansion, and drive the formation of egg-producing archegonia. Once initiating the meristem, hermaphrodites secrete the pheromone antheridiogen, which triggers neighboring slower-growing gametophytes to develop as males, while the hermaphrodites themselves remain insensitive to antheridiogen. This strategy promotes outcrossing and prevents all individuals in the colony from becoming males. This study reveals that an evolutionarily conserved GRAS domain transcriptional regulator (CrHAM), directly repressed by Ceratopteris microRNA171 (CrmiR171), promotes meristem development in Ceratopteris gametophytes and determines the male-to-hermaphrodite ratio in the colony. CrHAM preferentially accumulates within the meristems of hermaphrodites but is excluded from differentiated antheridia. CrHAM sustains meristem proliferation and cell division through conserved hormone pathways. In the meantime, CrHAM inhibits the antheridiogen-induced conversion of hermaphrodites to males by suppressing the male program expression and preventing meristem cells from differentiating into sperm-producing antheridia. This finding establishes a connection between meristem indeterminacy and sex determination in ferns, suggesting both conserved and diversified roles of meristem regulators in land plants. 

Accurate citywide crowd activity prediction (CAP) can enable proactive crowd mobility management and timely responses to urban events, which has become increasingly important for a myriad of smart city planning and management purposes. However, complex correlations across the crowd activities, spatial and temporal urban environment features and theirinteractivedependencies, and relevant external factors (e.g., weather conditions) make it highly challenging to predict crowd activities accurately in terms of different venue categories (for instance, venues related to dining, services, and residence) and varying degrees (e.g., daytime and nighttime).

To address the above concerns, we proposeSTICAP, a citywide spatio-temporal interactive crowd activity prediction approach. In particular,STICAPtakes in the location-based social network check-in data (e.g., from Foursquare/Gowalla) as the model inputs and forecasts the crowd activity within each time step for each venue category. Furthermore, we have integrated multiple levels of temporal discretization to interactively capture the relations with historical data. Then, three parallelResidual Spatial Attention Networks(RSAN) in theSpatial Attention Componentexploit the hourly, daily, and weekly spatial features of crowd activities, which are further fused and processed by theTemporal Attention Componentforinteractive CAP. Along with other external factors such as weather conditions and holidays,STICAPadaptively and accurately forecasts the final crowd activities per venue category, enabling potential activity recommendation and other smart city applications. Extensive experimental studies based on three different real-world crowd activity datasets have demonstrated that our proposedSTICAPoutperforms the baseline and state-of-the-art algorithms in CAP accuracy, with an average error reduction of 35.02%.

 

Leaf traits are essential for understanding many physiological and ecological processes. Partial least squares regression (PLSR) models with leaf spectroscopy are widely applied for trait estimation, but their transferability across space, time, and plant functional types (PFTs) remains unclear.

We compiled a novel dataset of paired leaf traits and spectra, with 47 393 records for > 700 species and eight PFTs at 101 globally distributed locations across multiple seasons. Using this dataset, we conducted an unprecedented comprehensive analysis to assess the transferability of PLSR models in estimating leaf traits.

While PLSR models demonstrate commendable performance in predicting chlorophyll content, carotenoid, leaf water, and leaf mass per area prediction within their training data space, their efficacy diminishes when extrapolating to new contexts. Specifically, extrapolating to locations, seasons, and PFTs beyond the training data leads to reducedR²(0.12–0.49, 0.15–0.42, and 0.25–0.56) and increased NRMSE (3.58–18.24%, 6.27–11.55%, and 7.0–33.12%) compared with nonspatial random cross‐validation. The results underscore the importance of incorporating greater spectral diversity in model training to boost its transferability.

These findings highlight potential errors in estimating leaf traits across large spatial domains, diverse PFTs, and time due to biased validation schemes, and provide guidance for future field sampling strategies and remote sensing applications.

 

According to classic stomatal optimization theory, plant stomata are regulated to maximize carbon assimilation for a given water loss. A key component of stomatal optimization models is marginal water‐use efficiency (mWUE), the ratio of the change of transpiration to the change in carbon assimilation. Although the mWUE is often assumed to be constant, variability of mWUE under changing hydrologic conditions has been reported. However, there has yet to be a consensus on the patterns of mWUE variabilities and their relations with atmospheric aridity. We investigate the dynamics of mWUE in response to vapor pressure deficit (VPD) and aridity index using carbon and water fluxes from 115 eddy covariance towers available from the global database FLUXNET. We demonstrate a non‐linear mWUE‐VPD relationship at a sub‐daily scale in general; mWUE varies substantially at both low and high VPD levels. However, mWUE remains relatively constant within the mid‐range of VPD. Despite the highly non‐linear relationship between mWUE and VPD, the relationship can be informed by the strong linear relationship between ecosystem‐level inherent water‐use efficiency (IWUE) and mWUE using the slope,m*. We further identify site‐specificm* and its variability with changing site‐level aridity across six vegetation types. We suggest accurately representing the relationship between IWUE and VPD using Michaelis–Menten or quadratic functions to ensure precise estimation of mWUE variability for individual sites.

 

Solar-induced chlorophyll fluorescence (SIF) is widely accepted as a proxy for gross primary productivity (GPP). Among the various SIF measurements, tower-based SIF measurements allow for continuous monitoring of SIF variation at a canopy scale with high temporal resolution, making it suitable for monitoring highly variable plant physiological responses to environmental changes. However, because of the strong and close relationship between SIF and absorbed photosynthetically active radiation (aPAR), it may be difficult to detect the influence of environmental drivers other than light conditions. Among the drivers, atmospheric dryness (vapor pressure deficit, VPD) is projected to increase as drought becomes more frequent and severe in the future, negatively impacting plants. In this study, we evaluated the tower-based high-frequency SIF measurement as a tool for detecting plant response to highly variable VPD. The study was performed in a mixed temperate forest in Virginia, USA, where a 40-m-tall flux tower has been measuring gas and energy exchanges and ancillary environmental drivers, and the Fluospec 2 system has been measuring SIF. We show that a proper definition of light availability to vegetation can reproduce SIF response to changing VPD that is comparable to GPP response as estimated from eddy covariance measurement: GPP decreased with rising VPD regardless of how aPAR was defined, whereas SIF decreased only when aPAR was defined as the PAR absorbed by chlorophyll (aPARchl) or simulated by a model (Soil Canopy Observation, Photochemistry and Energy fluxes, SCOPE). We simulated the effect of VPD on SIF with two different simulation modes of fluorescence emission representing contrasting moisture conditions, ‘Moderate’ and ‘Soil Moisture (SM) Stress’ modes. The decreasing SIF to rising VPD was only found in the SM Stress mode, implying that the SIF-VPD relationship depends on soil moisture conditions. Furthermore, we observed a similar response of SIF to VPD at hourly and daily scales, indicating that satellite measurements can be used to study the effects of environmental drivers other than light conditions. Finally, the definition of aPAR emphasizes the importance of canopy structure research to interpret remote sensing observations properly. 

Tuning the topology of two‐dimensional (2D) covalent organic frameworks (COFs) is of paramount scientific interest but remains largely unexplored. Herein, we present a site‐selective synthetic strategy that enables the tuning of 2D COF topology by simply adjusting the molar ratio of an amine‐functionalized dihydrazide monomer (NH₂−Ah) and 4,4′,4′′‐(1,3,5‐triazine‐2,4,6‐triyl)tribenzaldehyde (Tz). This approach resulted in the formation of two distinct COFs: a clover‐like 2D COF with free amine groups (NH₂−Ah−Tz) and a honeycomb‐like COF without amine groups (Ah−Tz). Both COFs exhibited good crystallinity and moderate porosity. Remarkably, the clover‐shaped NH₂−Ah−Tz COF, with abundant free amine groups, displayed significantly enhanced adsorption capacities toward crystal violet (CV, 261 mg/g) and congo red (CR, 1560 mg/g) compared to the non‐functionalized honeycomb‐like Ah−Tz COF (123 mg/g for CV and 1340 mg/g for CR), underscoring the pivotal role of free amine functional groups in enhancing adsorption capacities for organic dyes. This work highlights that the site‐selective synthetic strategy paves a new avenue for manipulating 2D COF topology by adjusting the monomer feeding ratio, thereby modulating their adsorption performances toward organic dyes.