The Relationship between Reference Crop Evapotranspiration Change Characteristics and Meteorological Factors in Typical Areas of the Middle of the Dry-Hot Valley of Jinsha River

Water, Год журнала: 2024, Номер 16(11), С. 1512 - 1512

Опубликована: Май 24, 2024

Reference crop evapotranspiration (ET0) is a key factor in ecohydrological processes. Studying the variation trend of ET0 arid river valleys and its influencing factors not only helpful to understanding response dry hot hydrological processes under background climate change but also has important guiding significance for efficient allocation soil water resources stable maintenance ecosystem this area. Based on daily meteorological data three representative stations middle Dry-hot Valley Jinsha River from 1988 2019, are analyzed by quantitative qualitative methods. The results showed that (1) significant fluctuating (Z > 1.98), linear rates were examined Huaping, Yuanmou, Panzhihua. (2) Grey correlation analysis principal component mutually verify mean temperature most influential factor. (3) sensitivity section sub-sections as follows: average temperature, relative humidity, wind speed, sunshine hours. sensitive followed strengthening speed reduction hours least. (4) Among regions, contributed increase Panzhihua, Yuanmou (6.086%), (8.468%) (3.869%), respectively. least

Язык: Английский

---

Estimating crop evapotranspiration of wheat-maize rotation system using hybrid convolutional bidirectional Long Short-Term Memory network with grey wolf algorithm in Chinese Loess Plateau region

Agricultural Water Management, Год журнала: 2024, Номер 301, С. 108924 - 108924

Опубликована: Июнь 28, 2024

Accurate estimation of crop evapotranspiration (ET) is essential for the efficient utilization agricultural water resources, production enhancement, and sustainable development. However, direct measurement ET highly expensive, intricate, time-consuming, highlighting imperative establishing a novel model to accurately estimate in ecosystems. To address above problems, this study proposed (GWA-CNN-BiLSTM), which incorporates Grey Wolf Algorithm (GWA), Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory network (BiLSTM) as hyperparameter adjuster, feature extractor, regression component, respectively, built upon various input combinations comprising net solar radiation (Rn), vapor pressure deficit (VPD), average air temperature (Ta), soil content (SWC), leaf area index (LAI) about winter wheat-spring maize rotation system during 2012–2020 Loess Plateau. Besides, following comparative assessment within GWA-CNN-BiLSTM, (CNN-BiLSTM), BiLSTM, (LSTM), Shuttleworth-Wallace (SW) models, results revealed that GWA-CNN-BiLSTM under varied inputs obtained superior performance, ranging from 0.562 0.957 determination coefficient (R2), 8.4–41.5 % relative root mean square error (RRMSE), 0.349 mm d−1 1.521 absolute (MAE), −3.26 14.11 percent bias (PBIAS), 0.820–1.091 (b0), respectively. Moreover, while accuracy BiLSTM over LSTM was evident, its performance notably improved by incorporation CNN module. Additionally, LSTM-type models complete combination present better precision than SW 29.7−51.4 R2, 44.2−76.1 RRMSE, 33.6−63.4 MAE, Furthermore, all exhibited excellence wheat compared spring maize, corresponding improvements ranged 1.4−4.3 5.1−20.1 3.1−17.9 meteorological factors (Rn, VPD, Ta) proved be most important maize. Wherein importance SWC exceeded LAI wheat, opposite trend observed In brief, recommended diverse data scenarios Plateau, can facilitate offer valuable assistance regional agriculture management decisions.

Язык: Английский

---

Construction of Big Data Information Security Protection System in Industrial Internet Environment

Applied Mathematics and Nonlinear Sciences, Год журнала: 2024, Номер 9(1)

Опубликована: Янв. 1, 2024

Abstract With the continuous development and integration of information technology industrialization-related technologies, industrial Internet control system security attacks occur frequently, it is more important to build an protection system. This study focuses on research improvement from two aspects access intrusion prevention designs strategy based homomorphic encryption algorithm Hyper Elliptic Curve Cryptosystem (HCC) key splitting threshold. Meanwhile, convolutional neural network, two-way gating loop unit, multi-head attention mechanism are integrated construct CMAG detection model. The model applied analyzed. decryption times this paper’s both relatively smooth, with average time consumption about 1.93ms 0.46ms, respectively, significantly better than other algorithms increase in number bits. throughput 13.68 KB/s, which approximately 2 times, 19 29 higher GM, ElGamal, Paillier algorithms, respectively. cannot match its rate during decryption. has accuracy 99.14%, that models, checking accuracy, recall, F1-Score 0.9889, 0.9783, 0.9834, 1.25%-5.16%, 4.31%-7.19%, 3.32%, compared three algorithms. 7.19% 3.32%-6.76%, paper great practical significance for construction optimization a big data environment.

Язык: Английский

---

Estimating and forecasting daily reference crop evapotranspiration in China with temperature-driven deep learning models

Agricultural Water Management, Год журнала: 2024, Номер 307, С. 109268 - 109268

Опубликована: Дек. 24, 2024

Язык: Английский

---