Search

Your search keyword '"Meng, Huimei"' showing total 4 results
Start Over Author "Meng, Huimei"
4 results on '"Meng, Huimei"'

1. Development of a Machine Learning Forecast Model for Global Horizontal Irradiation Adapted to Tibet Based on Visible All-Sky Imaging

Author

Wu, Lingxiao, primary, Chen, Tianlu, additional, Ciren, Nima, additional, Wang, Dui, additional, Meng, Huimei, additional, Li, Ming, additional, Zhao, Wei, additional, Luo, Jingxuan, additional, Hu, Xiaoru, additional, Jia, Shengjie, additional, Liao, Li, additional, Pan, Yubing, additional, and Wang, Yinan, additional

Published
2023
Full Text
View/download PDF

2. Construction and Research of Ultra-Short Term Prediction Model of Solar Short Wave Irradiance Suitable for Qinghai–Tibet Plateau.

Author

Meng, Huimei, Wu, Lingxiao, Li, Huaxia, and Song, Yixin

Subjects
*PREDICTION models, *BOX-Jenkins forecasting, *WIND forecasting, *SPRING, *AUTUMN, *SOLAR radiation, *SOLAR energy, *FORECASTING
Abstract

The Qinghai–Tibet Plateau region has abundant solar energy, which presents enormous potential for the development of solar power generation. Accurate prediction of solar radiation is crucial for the safe and cost-effective operation of the power grid. Therefore, constructing a suitable ultra-short-term prediction model for the Tibetan Plateau region holds significant importance. This study was based on the autoregressive integrated moving average model (ARIMA), random forest model (RF), and long short-term memory model (LSTM) to construct a prediction model for forecasting the average irradiance for the next 10 min. By locally testing and optimizing the model parameter, the study explored the applicability of each model in different seasons and investigates the impact of factors such as training dataset and prediction time range on model accuracy. The results showed that: (1) the accuracy of the ARIMA model was lower than the persistence model used as a reference model, while both the RF model and LSTM model had higher accuracy than the persistence model; (2) the sample size and distribution of the training dataset significantly affected the accuracy of the models. When both the season (distribution) and sample size were the same, RF achieved the highest accuracy. The optimal sample sizes for ARIMA, RF, and LSTM models in each season were as follows: spring (3564, 1980, 4356), summer (2772, 4752, 2772), autumn (3564, 3564, 4752), and winter (3168, 3168, 4752). (3) The prediction forecast horizon had a significant impact on the model accuracy. As the forecast horizon increased, the errors of all models gradually increased, reaching a peak between 80 and 100 min before slightly decreasing and then continuing to rise. When both the season and forecast horizon were the same, RF had the highest accuracy, with an RMSE lower than ARIMA by 65.6–258.3 W/m2 and lower than LSTM by 3.7–83.3 W/m2. Therefore, machine learning can be used for ultra-short-term forecasting of solar irradiance in the Qinghai–Tibet Plateau region to meet the forecast requirements for solar power generation, providing a reference for similar studies. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

4. An evolutionary habitat selection by the plateau pika (Ochotona curzoniae) in relation to the niche construction of the livestock management on the Qinghai-Tibetan plateau

Author

Ma Hong-Mei, Wu Qianqian, Tahi Ghaltso, Jennifer Watts, Han Hui, La Qiong, Pan Xuan, Meng Huimei, Liu Mengjun, Song Xuanzi, Migmar Wangdwei, Cao Rui, and Deching Wangmo

Subjects
geography, Niche construction, Plateau, geography.geographical_feature_category, biology, Occupancy, Habitat, Ecology, Ochotona curzoniae, Biodiversity, Kobresia, Pika, biology.organism_classification
Abstract

Habitat selection by animals is conventionally linked with nature selection pressures. However, niche construction as a potent evolutionary agent palys a crucial role for many types of evolutionary habitat selection by species and this modifies nature selection pressures. We used data obtained from an 11-year period to observe the evolutionary habitat selection by the plateau pika (Ochotona curzoniae) in relation to the niche construction of livestock management. We hypothesized that the niche construction of local nomads affects the evolutionary habitat selection of the plateau pika, and furthermore that the plateau pika does not fit niche conservatism in the Kobresia ecosystem of the Qinghai Tibetan Plateau (QTP). In order to verify the above hypotheses, we used the distance to the nearest yak-bedding areas and dung management as the variables that most strongly explain variation in pika occupancy (probability) and detection probability based on free-ranging livestock. Both pika occupancy and detection probability decrease sharply with increasing distance to the nearest yak-bedding area, suggesting that pika population densities are highest closest to yak-bedding areas. There is a strong correlation between dung cover and occupancy of the plateau pika; the more dung drying on the ground, the more plateau pikas occupy the area. Consequently, the plateau pika is frequently detected in damaged grass. Rangeland dominated by Kobresia sedges on the QTP is modified by livestock grazing and management, especially by dung management. This is the first research suggesting that local nomads may cause expansion of the habitat of the plateau pika. In sum, the habitat of the plateau pika is expanding and there is strong evidence that it retains its biodiversity on the Qinghai-Tibetan Plateau in spite of exposure to poison as control measure. Still, the current control management of the plateau pika may result in diminished diversity of both fauna and flora species and a collapse of the food web on the QTP.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results