Solar-induced chlorophyll fluorescence (SIF) is a direct proxy for photosynthetic activity, yet existing satellite SIF products are constrained by coarse spatial resolution, limiting their application in ecological and agricultural studies. In this work, we propose a One-Step Learned Spatial Redistribution Convolutional Neural Network (OSRNet) that downscales 0.05° TROPOMI SIF to 0.005° by learning spatially adaptive redistribution fields from high-resolution drivers, which allocate coarse-resolution satellite SIF into fine-resolution grids. Based on this framework, we generate RSIF, a global 16-day 0.005° SIF dataset for 2018–2020. Comprehensive evaluation against both satellite and tower-based SIF shows that RSIF maintains strong consistency with TROPOMI observations (R² = 0.976, RMSE = 0.036) while recovering fine-scale spatial details. OSRNet substantially outperforms established direct prediction methods such as RF and SIFNet, and, compared with post hoc corrected RF approach from prior studies, achieves the highest R² across all tower sites and generally the lowest RMSE, enabling more accurate representation of seasonal dynamics with improved spatial fidelity.

The recent success of 3D Gaussian Splatting (3DGS) on the task of novel view synthesis has amazed every one with its photorealistic results with high training and rendering speed. This paper aims to increase the interpretability of the model in both geometric attribute and appearances by a simple yet effective method: lifting constraints on color features of each splat. This enables more accurate guidance from monocular depth prediction models and strengthen the ability of model to reconstruct scene geometry. Experiments shows that this effectively reduces indeterminacy of the reconstruction problem and allows better understanding of the scene structure and individual, especially in scenes with limited viewpoints, while maintaining high-fidelity rendering even in some of the uncovered views.

Inherent optical properties (IOPs) are crucial parameters for assessing water quality, with widely applied estimation methods established for open oceans. The estimation of IOPs for inland and coastal waters, however, remains a longstanding challenge due to their complex optical properties. In order to address this, we developed a deep learning-assisted quasi-analytical algorithm (QAA-DL) for estimating IOPs in inland and coastal waters. This method enhances traditional QAA procedures by using a neural network to reparameterize the algorithm for extremely turbid waters. Additionally, we introduced a soft-wired classification scheme to ensure smooth retrieval of IOPs in slightly turbid waters. Validation analyses showed that the IOPs retrievals using QAA-DL agreed well with the worldwide in situ measurements. Compared to other standard IOPs algorithms, QAA-DL provided more than double the valid data coverage in turbid waters. Additionally, when applied to moderate resolution imaging spectroradiometer (MODIS) imagery, the QAA-DL algorithm demonstrates consistent spatial patterns in IOPs retrievals. The QAA-DL algorithm can be adopted in different ocean color missions to produce high-quality IOPs retrievals for global inland and coastal waters.

The latest breakthroughs in spatially resolved transcriptomics technology offer comprehensive opportunities to delve into gene expression patterns within the tissue microenvironment. However, the precise identification of spatial domains within tissues remains challenging. In this study, we introduce AttentionVGAE (AVGN), which integrates slice images, spatial information and raw gene expression while calibrating low-quality gene expression. By combining the variational graph autoencoder with multi-head attention blocks (MHA blocks), AVGN captures spatial relationships in tissue gene expression, adaptively focusing on key features and alleviating the need for prior knowledge of cluster numbers, thereby achieving superior clustering performance. Particularly, AVGN attempts to balance the model's attention focus on local and global structures by utilizing MHA blocks, an aspect that current graph neural networks have not extensively addressed. Benchmark testing demonstrates its significant efficacy in elucidating tissue anatomy and interpreting tumor heterogeneity, indicating its potential in advancing spatial transcriptomics research and understanding complex biological phenomena.

Intensive blooms of floating macroalgae have been widely reported during the past decades. Multispectral satellite imagery serves as an important data source for bloom monitoring, but its capacities are often hindered by the difficulties in accurate cloud or cloud shadow masking. Imperfect masking not only leads to a lack of bloom observations but also induces uncertainties in their biomass estimations. To reduce false detections and to retain more valid satellite measurements, the feedback attention network (FANet) was applied to mask cloud and cloud shadow pixels on Moderate Resolution Imaging Spectroradiometer (MODIS) imagery. Satisfactory performance was achieved on the images taken in the Caribbean Sea, where cloud and sun glint contaminations frequently occur. The overall cloud detection accuracy is ~96%, as referred to manually prepared “ground truth”. Cloud shadows are effectively detected while overmasking near sun glint regions is reduced. Compared with the commonly used SeaWiFS Data Analysis System (SeaDAS) cloud products, the FANet-derived cloud products retain 44% more valid MODIS measurements in summer 2021. Consequently, they consistently provide more macroalgal features on each single MODIS image. However, the monthly mean macroalgae biomass statistics derived from these two cloud masking approaches are consistently close despite their large differences in the number of valid measurements, suggesting that the mean-value composite strategy can minimize the impact of missing observations and provide reliable long-term trends. The proposed cloud masking method is also applicable to other similar multispectral sensors [i.e., Visible Infrared Imaging Radiometer Suite (VIIRS)] for monitoring floating macroalgae in the global open oceans.

Frequent Sargassum beaching in the Caribbean Sea and other regions has caused severe problems for local environments and economies. Although coarse-resolution satellite instruments can provide large-scale Sargassum distributions, their use is problematic in nearshore waters that are directly relevant to local communities. Finer resolution instruments, such as the multispectral instruments (MSIs) on the Sentinel-2 satellites, show potential to fill this gap, yet automatic Sargassum extraction is difficult due to compounding factors. In this article, a new approach is developed to extract Sargassum features automatically from MSI Floating Algae Index (FAI) images. Because of the high spatial resolution, limited signal-to-noise ratio (SNR), and staggered instrument internal configuration, there are many nonalgae bright targets (including cloud artifacts and wave-induced glints) causing enhanced near-infrared reflectance and elevated FAI values. Based on the spatial patterns of these image “noises,” a Trainable Nonlinear Reaction Diffusion (TNRD) denoising model is trained to estimate and remove such noise. The model shows excellent performance when tested over realistic noise patterns derived from MSI measurements. After removing such noise and masking clouds (as well as cloud shadows and glint patterns), biomass density from each valid pixel is quantified using the FAI-biomass model established from earlier field measurements, from which Sargassum morphology (length/width/biomass) is derived. Overall, the proposed approach achieves over 86% Sargassum extraction accuracy and shows preliminary success on Landsat-8 images. The approach is expected to be incorporated in the existing near real-time Sargassum Watch System for both Landsat-8 and Sentinel-2 observations to monitor Sargassum over nearshore waters.

Satellite images of reflected sunlight have been used to detect and monitor oil spills in oceans. However, such a capacity is often hindered by the image noise due to either a low signal-to-noise ratio or other image features such as clouds or cloud shadows. The problem is particularly severe for nighttime images captured by the Visible Infrared Imager Radiometer Suite (VIIRS). This letter proposes a practical method to extract oil slick features in a semiautomatic fashion from VIIRS nighttime images and other noisy optical remote sensing images. The method is based on statistical information and morphological operators, and it is demonstrated to be able to effectively remove the noise and identify line features with the appropriate selection of threshold values. Testing this method over VIIRS nighttime images shows the preliminary success of oil slick feature extraction. Experiments on daytime data collected by the Moderate Resolution Imaging Spectroradiometer (MODIS) also suggest the applicability of this method to other optical remote sensing images. However, the requirement of human intervention to determine optimal parameters points to the need for improved automation in future works.

We consider a multilingual weakly supervised learning scenario where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide the learning in other languages. Past approaches project labels across bitext and use them as features or gold labels for training. We propose a new method that projects model expectations rather than labels, which facilities transfer of model uncertainty across language boundaries. We encode expectations as constraints and train a discriminative CRF model using Generalized Expectation Criteria (Mann and McCallum, 2010). Evaluated on standard Chinese-English and German-English NER datasets, our method demonstrates F1 scores of 64% and 60% when no labeled data is used. Attaining the same accuracy with supervised CRFs requires 12k and 1.5k labeled sentences. Furthermore, when combined with labeled examples, our method yields significant improvements over state-of-the-art supervised methods, achieving best reported numbers to date on Chinese OntoNotes and German CoNLL-03 datasets.

Most semi-supervised methods in Natural Language Processing capitalize on unannotated resources in a single language; however, information can be gained from using parallel resources in more than one language, since translations of the same utterance in different languages can help to disambiguate each other. We demonstrate a method that makes effective use of vast amounts of bilingual text (a.k.a. bitext) to improve monolingual systems. We propose a factored probabilistic sequence model that encourages both crosslanguage and intra-document consistency. A simple Gibbs sampling algorithm is introduced for performing approximate inference. Experiments on English-Chinese Named Entity Recognition (NER) using the OntoNotes dataset demonstrate that our method is significantly more accurate than state-ofthe- art monolingual CRF models in a bilingual test setting. Our model also improves on previous work by Burkett et al. (2010), achieving a relative error reduction of 10.8% and 4.5% in Chinese and English, respectively. Furthermore, by annotating a moderate amount of unlabeled bi-text with our bilingual model, and using the tagged data for uptraining, we achieve a 9.2% error reduction in Chinese over the state-ofthe- art Stanford monolingual NER system.

Aju Thalappillil Scaria, Jonathan Berant, Mengqiu Wang, Peter Clark, Justin Lewis, Brittany Harding, Christopher D. Manning. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. 2013.

NLP models have many and sparse features, and regularization is key for balancing model overfitting versus underfitting.A recently repopularized form of regularization is to generate fake training data by repeatedly adding noise to real data.We reinterpret this noising as an explicit regularizer, and approximate it with a second-order formula that can be used during training without actually generating fake data.We show how to apply this method to structured prediction using multinomial logistic regression and linear-chain CRFs.We tackle the key challenge of developing a dynamic program to compute the gradient of the regularizer efficiently.The regularizer is a sum over inputs, so we can estimate it more accurately via a semi-supervised or transductive extension.Applied to text classification and NER, our method provides a >1% absolute performance gain over use of standard L 2 regularization.

While social interactions are critical to understanding consumer behavior, the relationship between social and commerce networks has not been explored on a large scale. We analyze Taobao, a Chinese consumer marketplace that is the world's largest e-commerce website. What sets Taobao apart from its competitors is its integrated instant messaging tool, which buyers can use to ask sellers about products or ask other buyers for advice. In our study, we focus on how an individual's commercial transactions are embedded in their social graphs. By studying triads and the directed closure process, we quantify the presence of information passing and gain insights into when different types of links form in the network.

We describe probabilistic models that leverage individual blog post evidence to improve blog seed retrieval performances. Our model offers a intuitive and principled method to combine multiple posts in scoring a whole blog site by treating individual posts as hidden variables. When applied to the seed retrieval task, our model yields state-of-the-art results on the TREC 2007 Blog Distillation Task dataset.

The approach of using passage-level evidence for document retrieval has shown mixed results when it is applied to a variety of test beds with different characteristics. One main reason of the inconsistent performance is that there exists no unified framework to model the evidence of individual passages within a document. This paper proposes two probabilistic models to formally model the evidence of a set of top ranked passages in a document. The first probabilistic model follows the retrieval criterion that a document is relevant if any passage in the document is relevant, and models each passage independently. The second probabilistic model goes a step further and incorporates the similarity correlations among the passages. Both models are trained in a discriminative manner. Furthermore, we present a combination approach to combine the ranked lists of document retrieval and passage-based retrieval.

We present a novel classifier-based deterministic parser for Chinese constituency parsing. Our parser computes parse trees from bottom up in one pass, and uses classifiers to make shift-reduce decisions. Trained and evaluated on the standard training and test sets, our best model (using stacked classifiers) runs in linear time and has labeled precision and recall above 88% using gold-standard part-of-speech tags, surpassing the best published results. Our SVM parser is 2-13 times faster than state-of-the-art parsers, while producing more accurate results. Our Maxent and DTree parsers run at speeds 40-270 times faster than state-of-the-art parsers, but with 5-6% losses in accuracy.

Forcing all IP packets to carry correct source addresses can greatly help network security, attack tracing, and network problem debugging. However, due to asymmetries in today's Internet routing, routers do not have readily available information to verify the correctness of the source address for each incoming packet. In this paper we describe a new protocol, named SAVE, that can provide routers with the information needed for source address validation. SAVE messages propagate valid source address information from the source location to all destinations, allowing each router along the way to build an incoming table that associates each incoming interface of the router with a set of valid source address blocks. This paper presents the protocol design and evaluates its correctness and performance by simulation experiments. The paper also discusses the issues of protocol security, the effectiveness of partial SAVE deployment, and the handling of unconventional forms of network routing, such as mobile IP and tunneling.