Search Results (8)

End-to-end relation extraction (E2ERE) generally performs named entity recognition and relation extraction either simultaneously or sequentially. While numerous studies on E2ERE have centered on enhancing span representations to improve model performance, challenges remain due to the gaps between subtasks (named entity recognition and relation extraction) and the modeling discrepancies between entities and relations. In this paper, we propose a novel Label Annotation Interaction-based representation enhancement method for E2ERE, which institutes a two-phase semantic interaction to augment representations. Specifically, we firstly feed label annotations that are easy to manually annotate into a language model, and conduct the first-round interaction between three types of tokens with a partial attention mechanism; Then we construct a latent multi-view graph to capture various possible links between label and entity (pair) nodes, facilitating the second-round interaction between entities and labels. A series of comparative experiments with methods of various transformer-based architectures currently in use show that LAI-Net can maintain performance on par with the current SOTA in terms of NER task, and achieves significant improvements over existing SOTA models in terms of RE task. Full article

In response to the issues of high complexity and low efficiency associated with the current reliance on manual sampling and instrumental measurement for obtaining maize leaf area index (LAI), this study constructed a maize image dataset comprising 624 images from three growth stages of summer maize in the Henan region, namely the jointing stage, small trumpet stage, and large trumpet stage. Furthermore, a maize LAI estimation model named LAINet, based on an improved convolutional neural network (CNN), was proposed. LAI estimation was carried out at these three key growth stages. In this study, the output structure was improved based on the ResNet architecture to adapt to regression tasks. The Triplet module was introduced to achieve feature fusion and self-attention mechanisms, thereby enhancing the accuracy of maize LAI estimation. The model structure was adjusted to enable the integration of growth-stage information, and the loss function was improved to accelerate the convergence speed of the network model. The model was validated on the self-constructed dataset. The results showed that the incorporation of attention mechanisms, integration of growth-stage information, and improvement of the loss function increased the model’s R² by 0.04, 0.15, and 0.05, respectively. Among these, the integration of growth-stage information led to the greatest improvement, with the R² increasing directly from 0.54 to 0.69. The improved model, LAINet, achieved an R² of 0.81, which indicates that it can effectively estimate the LAI of maize. This model can provide information technology support for the phenotypic monitoring of field crops. Full article

We proposed a direct approach to validate hectometric and kilometric resolution leaf area index (LAI) products that involved the scaling up of field-measured LAI via the validation and recalibration of the decametric Sentinel-2 LAI product. We applied it over a test study area of maize crops in northern China using continuous field measurements of LAINet along the year 2019. Sentinel-2 LAI showed an overall accuracy of 0.67 in terms of Root Mean Square Error (RMSE) and it was used, after recalibration, as a benchmark to validate six coarse resolution LAI products: MODIS, Copernicus Global Land Service 1 km Version 2 (called GEOV2) and 300 m (GEOV3), Satellite Application Facility EUMETSAT Polar System (SAF EPS) 1.1 km, Global LAnd Surface Satellite (GLASS) 500 m and Copernicus Climate Change Service (C3S) 1 km V2. GEOV2, GEOV3 and MODIS showed a good agreement with reference LAI in terms of magnitude (RMSE ≤ 0.29) and phenology. SAF EPS (RMSE = 0.68) and C3S V2 (RMSE = 0.41), on the opposite, systematically underestimated high LAI values and showed systematic differences for phenological metrics: a delay of 6 days (d), 20 d and 24 d for the start, peak and the end of growing season, respectively, for SAF EPS and an advance of −4 d, −6 d and −6 d for C3S. Full article

Accurate and continuous monitoring of leaf area index (LAI), a widely-used vegetation structural parameter, is crucial to characterize crop growth conditions and forecast crop yield. Meanwhile, advancements in collecting field LAI measurements have provided strong support for validating remote-sensing-derived LAI. This paper evaluates the performance of LAI retrieval from multi-source, remotely sensed data through comparisons with continuous field LAI measurements. Firstly, field LAI was measured continuously over periods of time in 2018 and 2019 using LAINet, a continuous LAI measurement system deployed using wireless sensor network (WSN) technology, over an agricultural region located at the Heihe watershed at northwestern China. Then, cloud-free images from optical satellite sensors, including Landsat 7 the Enhanced Thematic Mapper Plus (ETM+), Landsat 8 the Operational Land Imager (OLI), and Sentinel-2A/B Multispectral Instrument (MSI), were collected to derive LAI through inversion of the PROSAIL radiation transfer model using a look-up-table (LUT) approach. Finally, field LAI data were used to validate the multi-temporal LAI retrieved from remote-sensing data acquired by different satellite sensors. The results indicate that good accuracy was obtained using different inversion strategies for each sensor, while Green Chlorophyll Index (CIgreen) and a combination of three red-edge bands perform better for Landsat 7/8 and Sentinel-2 LAI inversion, respectively. Furthermore, the estimated LAI has good consistency with in situ measurements at vegetative stage (coefficient of determination R² = 0.74, and root mean square error RMSE = 0.53 m² m⁻²). At the reproductive stage, a significant underestimation was found (R² = 0.41, and 0.89 m² m⁻² in terms of RMSE). This study suggests that time-series LAI can be retrieved from multi-source satellite data through model inversion, and the LAINet instrument could be used as a low-cost tool to provide continuous field LAI measurements to support LAI retrieval. Full article

Many applications, including crop growth and yield monitoring, require accurate long-term time series of leaf area index (LAI) at high spatiotemporal resolution with a quantification of the associated uncertainties. We propose an LAI retrieval approach based on a combination of the LAINet observation system, the Consistent Adjustment of the Climatology to Actual Observations (CACAO) method, and Gaussian process regression (GPR). First, the LAINet wireless sensor network provides temporally continuous field measurements of LAI. Then, the CACAO approach generates synchronous reflectance data at high spatiotemporal resolution (30-m and 8-day) from the fusion of multitemporal MODIS and high spatial resolution Landsat satellite imagery. Finally, the GPR machine learning regression algorithm retrieves the LAI maps and their associated uncertainties. A case study in a cropland site in China showed that the accuracy of LAI retrievals is 0.36 (12.7%) in terms of root mean square error and R² = 0.88 correlation with ground measurements as evaluated over the entire growing season. This paper demonstrates the potential of the joint use of newly developed software and hardware technologies in deriving concomitant LAI and uncertainty maps with high spatiotemporal resolution. It will contribute to precision agriculture, as well as to the retrieval and validation of LAI products. Full article

Spatiotemporally representative Elementary Sampling Units (ESUs) are required for capturing the temporal variations in surface spatial heterogeneity through field measurements. Since inaccessibility often coexists with heterogeneity, a cost-efficient sampling design is mandatory. We proposed a sampling strategy to generate spatiotemporally representative and cost-efficient ESUs based on the conditioned Latin hypercube sampling scheme. The proposed strategy was constrained by multi-temporal Normalized Difference Vegetation Index (NDVI) imagery, and the ESUs were limited within a sampling feasible region established based on accessibility criteria. A novel criterion based on the Overlapping Area (OA) between the NDVI frequency distribution histogram from the sampled ESUs and that from the entire study area was used to assess the sampling efficiency. A case study in Wanglang National Nature Reserve in China showed that the proposed strategy improves the spatiotemporally representativeness of sampling (mean annual OA = 74.7%) compared to the single-temporally constrained (OA = 68.7%) and the random sampling (OA = 63.1%) strategies. The introduction of the feasible region constraint significantly reduces in-situ labour-intensive characterization necessities at expenses of about 9% loss in the spatiotemporal representativeness of the sampling. Our study will support the validation activities in Wanglang experimental site providing a benchmark for locating the nodes of automatic observation systems (e.g., LAINet) which need a spatially distributed and temporally fixed sampling design. Full article

In this study, an algorithm to retrieve the gravimetric vegetation water content (GVWC, %) of corn was developed. First, the method for obtaining the optical depth from L-band (1.4 GHz) bi-angular, dual-polarized brightness temperatures (TB) for short vegetation was investigated. Then, the quantitative relationship between the corn optical depth, corn GVWC and corn leaf area index (LAI) was constructed. Finally, using the Polarimetric L-band Microwave Radiometer (PLMR) airborne data in the 2012 Heihe Watershed Allied Telemetry Experimental Research (HiWATER) project, the Global Land Surface Satellite (GLASS) LAI product, the height and areal density of the corn stalks, the corn GVWC was estimated (corn GLASS-GVWC). Both the in situ measured corn GVWC and the corn GVWC retrieved based on the in situ measured corn LAI (corn LAINET-GVWC) were used to validate the accuracy of the corn GLASS-GVWC. The results show that the GVWC retrieval method proposed in this study is feasible for monitoring the corn GVWC. However, the accuracy of the retrieval results is highly sensitive to the accuracy of the LAI input parameters. Full article

A sampling strategy to define elementary sampling units (ESUs) for an entire site at the kilometer scale is an important step in the validation process for moderate-resolution leaf area index (LAI) products. Current LAI-sampling strategies are unable to consider the vegetation seasonal changes and are better suited for single-day LAI product validation, whereas the increasingly used wireless sensor network for LAI measurement (LAINet) requires an optimal sampling strategy across both spatial and temporal scales. In this study, we developed an efficient and robust LAI Sampling strategy based on Multi-temporal Prior knowledge (SMP) for long-term, fixed-position LAI observations. The SMP approach employed multi-temporal vegetation index (VI) maps and the vegetation classification map as a priori knowledge. The SMP approach minimized the multi-temporal bias of the VI frequency histogram between the ESUs and the entire site and maximized the nearest-neighbor index to ensure that ESUs were dispersed in the geographical space. The SMP approach was compared with four sampling strategies including random sampling, systematic sampling, sampling based on the land-cover map and a sampling strategy based on vegetation index prior knowledge using the PROSAIL model-based simulation analysis in the Heihe River basin. The results indicate that the ESUs selected using the SMP method spread more evenly in both the multi-temporal feature space and geographical space over the vegetation cycle. By considering the temporal changes in heterogeneity, the average root-mean-square error (RMSE) of the LAI reference maps can be reduced from 0.12 to 0.05, and the relative error can be reduced from 6.1% to 2.2%. The SMP technique was applied to assign the LAINet ESU locations at the Huailai Remote Sensing Experimental Station in Beijing, China, from 4 July to 28 August 2013, to validate three MODIS C5 LAI products. The results suggest that the average R², RMSE, bias and relative uncertainty for the three MODIS LAI products were 0.60, 0.33, −0.11, and 12.2%, respectively. The MCD15A2 product performed best, exhibiting a RMSE of 0.20, a bias of −0.07 and a relative uncertainty of 7.4%. Future efforts are needed to obtain more long-term validation datasets using the SMP approach on different vegetation types for validating moderate-resolution LAI products in time series. Full article