RESUMEN
Named entity recognition is a fundamental subtask for knowledge graph construction and question-answering in the agricultural diseases and pests field. Although several works have been done, the scarcity of the Chinese annotated dataset has restricted the development of agricultural diseases and pests named entity recognition(ADP-NER). To address the issues, a large-scale corpus for the Chinese ADP-NER task named AgCNER was first annotated. It mainly contains 13 categories, 206,992 entities, and 66,553 samples with 3,909,293 characters. Compared with other datasets, AgCNER maintains the best performance in terms of the number of categories, entities, samples, and characters. Moreover, this is the first publicly available corpus for the agricultural field. In addition, the agricultural language model AgBERT is also fine-tuned and released. Finally, the comprehensive experimental results showed that BiLSTM-CRF achieved F1-score of 93.58%, which would be further improved to 94.14% using BERT. The analysis from multiple aspects has verified the rationality of AgCNER and the effectiveness of AgBERT. The annotated corpus and fine-tuned language model are publicly available at https://doi.org/XXX and https://github.com/guojson/AgCNER.git .
Asunto(s)
Agricultura , China , Pueblos del Este de AsiaRESUMEN
Soil organic carbon (SOC) is vital for the global carbon cycle and environmentally sustainable development. Meanwhile, the fast, convenient remote sensing technology has become one of the notable means to monitor SOC content. Nowadays, limitations are found in the inversion of SOC content with high-precision and complex spatial relationships based on scarce ground sample points. It is restrained by the spatial difference in the relationship between SOC content and remote sensing spectra due to the problem of different spectra for the same substance and the influence of topographic and environment (e.g. vegetation and climate). In this regard, the two-point machine learning (TPML) method, which can overcome above problems and deal with complex spatial heterogeneity of relationships between SOC and remote sensing spectra, is used to invert the SOC content in Hailun County, Heilongjiang Province, combined with derived variables from Sentinel-1, Sentinel-2, topography and environment. Based on 10-fold cross-validation and t-test, results indicate that the TPML method boasts the highest inversion accuracy, followed by random forest, gradient boosting regression tree, partial least squares regression and support vector machine. The average r, MAE, RMSE, and RPD of TPML are 0.854, 0.384 %, 0.558 %, and 1.918. Further, the TPML method has been proven to be equal to evaluating the uncertainty of inversion results, by comparing the actual and theoretical error of the inversion result in one subset. The spatial inversion result of SOC content with 10 m resolution by TPML is smoother and has more real details than other models, which are consistent with the distribution of SOC content in different land use types. This study provides both theoretical and technical guidance for using TPML method combined with spectral information of remote sensing to predict soil attributes and offer accurate uncertainty estimation, thereby opening up the opportunity for low-cost, high-precision, and large-scale SOC inversion.
RESUMEN
Characterizing the relationship between vegetation phenology and urbanization indicators is essential to understand the impacts of human activities on urban ecosystems. In this study, we explored the response of vegetation phenology to urbanization in Beijing (China) during 2001-2018, using impervious surface area (ISA) and the information of urban-rural gradients (i.e., concentric rings from the urban core to surrounding rural areas) as the urbanization indicators. We found the change rates of vegetation phenology in urban areas are 1.3 and 1.1 days per year for start of season (SOS) and end of season (EOS), respectively, about three times faster than that in forest. Moreover, we found a divergent response of SOS with the increase of ISA, which differs from previous results with advanced SOS in the urban environment than surrounding rural areas. This might be attributed to the mixed land cover types and the thermal environment caused by the urban heat island in the urban environment. Similarly, a divergent pattern of phenological indicators along the urban-rural gradient shows a non-linear response of vegetation phenology to urbanization. These findings provide new insights into the complicated interactions between vegetation phenology and urban environments. High-resolution weather data are required to support process-based vegetation phenology models in the future, particularly under different global urbanization and climate change scenarios.