Search for: All records

Fern gametophytes are autotrophic and independent of sporophytes, and they develop pluripotent meristems that drive prothallus development and sexual reproduction. To reveal cellular dynamics during meristem development in fern gametophytes, we performed long-term time-lapse imaging and determined the real-time lineage, identity and division activity of each single cell from meristem initiation to establishment in gametophytes of the fernCeratopteris richardii. Our results demonstrate that in Ceratopteris gametophytes, only a few cell lineages originated from the marginal layer contribute to meristem initiation and proliferation, and the meristem lacks a distinguishable central zone or apical cell with low division activity. Within the meristem, cell division is independent of cell lineages and cells at the marginal layer are more actively dividing than inner cells. Furthermore, the meristem triggers differentiation of adjacent cells into egg-producing archegonia in a position-dependent manner. These findings advance the understanding of diversified meristem and gametophyte development in land plants.

 

Abstract Meristems in land plants share conserved functions but develop highly variable structures. Meristems in seed-free plants, including ferns, usually contain one or a few pyramid-/wedge-shaped apical cells (ACs) as initials, which are lacking in seed plants. It remained unclear how ACs promote cell proliferation in fern gametophytes and whether any persistent AC exists to sustain fern gametophyte development continuously. Here, we uncovered previously undefined ACs maintained even at late developmental stages in fern gametophytes. Through quantitative live-imaging, we determined division patterns and growth dynamics that maintain the persistent AC in Sphenomeris chinensis , a representative fern. The AC and its immediate progenies form a conserved cell packet, driving cell proliferation and prothallus expansion. At the apical centre of gametophytes, the AC and its adjacent progenies display small dimensions resulting from active cell division instead of reduced cell expansion. These findings provide insight into diversified meristem development in land plants. 

Neural methods are state-of-the-art for urban prediction problems such as transportation resource demand, accident risk, crowd mobility, and public safety. Model performance can be improved by integrating exogenous features from open data repositories (e.g., weather, housing prices, traffic, etc.), but these uncurated sources are often too noisy, incomplete, and biased to use directly. We propose to learn integrated representations, called EquiTensors, from heterogeneous datasets that can be reused across a variety of tasks. We align datasets to a consistent spatio-temporal domain, then describe an unsupervised model based on convolutional denoising autoencoders to learn shared representations. We extend this core integrative model with adaptive weighting to prevent certain datasets from dominating the signal. To combat discriminatory bias, we use adversarial learning to remove correlations with a sensitive attribute (e.g., race or income). Experiments with 23 input datasets and 4 real applications show that EquiTensors could help mitigate the effects of the sensitive information embodied in the biased data. Meanwhile, applications using EquiTensors outperform models that ignore exogenous features and are competitive with "oracle" models that use hand-selected datasets. 

Abstract The alternation of generations in land plants occurs between the sporophyte phase and the gametophyte phase. The sporophytes of seed plants develop self-maintained, multicellular meristems, and these meristems determine plant architecture. The gametophytes of seed plants lack meristems and are heterotrophic. In contrast, the gametophytes of seed-free vascular plants, including ferns, are autotrophic and free-living, developing meristems to sustain their independent growth and proliferation. Compared with meristems in the sporophytes of seed plants, the cellular mechanisms underlying meristem development in fern gametophytes remain largely unknown. Here, using confocal time-lapse live imaging and computational segmentation and quantification, we determined different patterns of cell divisions associated with the initiation and proliferation of two distinct types of meristems in gametophytes of two closely related Pteridaceae ferns, Pteris vittata and Ceratopteris richardii. Our results reveal how the simple timing of a switch between two meristems has considerable consequences for the divergent gametophyte morphologies of the two ferns. They further provide evolutionary insight into the function and regulation of gametophyte meristems in seed-free vascular plants. 

Emerging transportation modes, including car-sharing, bike-sharing, and ride-hailing, are transforming urban mobility yet have been shown to reinforce socioeconomic inequity. These services rely on accurate demand prediction, but the demand data on which these models are trained reflect biases around demographics, socioeconomic conditions, and entrenched geographic patterns. To address these biases and improve fairness, we present FairST, a fairness-aware demand prediction model for spatiotemporal urban applications, with emphasis on new mobility. We use 1D (time-varying, space-constant), 2D (space-varying, time-constant) and 3D (both time- and space-varying) convolutional branches to integrate heterogeneous features, while including fairness metrics as a form of regularization to improve equity across demographic groups. We propose two spatiotemporal fairness metrics, region-based fairness gap (RFG), applicable when demographic information is provided as a constant for a region, and individual-based fairness gap (IFG), applicable when a continuous distribution of demographic information is available. Experimental results on bike share and ride share datasets show that FairST can reduce inequity in demand prediction for multiple sensitive attributes (i.e. race, age, and education level), while achieving better accuracy than even state-of-the-art fairness-oblivious methods. 

This paper reviews the methods and findings of mobility equity studies, with a focus on new mobility. 

We present a fairness-aware model for predicting demand for new mobility systems. Our approach, called FairST, consists of 1D, 2D and 3D convolutions to learn the spatial-temporal dynamics of a mobility system, and fairness regularizers that guide the model to make equitable predictions. We propose two fairness metrics, region-based fairness gap (RFG) and individual-based fairness gap (IFG), that measure equity gaps between social groups for new mobility systems. Experimental results on two real-world datasets demonstrate the effectiveness of the proposed model: FairST not only reduces the fairness gap by more than 80%, but achieves better accuracy than state-of-the-art but fairness-oblivious methods including LSTMs, ConvLSTMs, and 3D CNN.