Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: obfitość

Sortuj według:

Ogranicz wyniki do:

Application of Multiboost-KELM algorithm to alleviate the collinearity of log curves for evaluating the abundance of organic matter in marine mud shale reservoirs: a case study in Sichuan Basin, China

Zhu L., Zhang C., Zhang C., Zhou X., Wang J., Wang X.

Acta Geophysica

2018

Vol. 66, no. 5

983--1000

The total organic carbon (TOC) content reflects the abundance of organic matter in marine mud shale reservoirs and reveals the hydrocarbon potential of the reservoir. Traditional TOC calculation methods based on statistical and machine learning have limited effect in improving the computational accuracy of marine mud shale reservoirs. In this study, the collinearity between log curves of marine mud shale reservoirs was revealed for the first time, which was found to be adverse to the improvement of TOC calculation accuracy. To this end, a new TOC prediction method was proposed based on Multiboost-Kernel extreme learning machine (Multiboost-KELM) bridging geostatistics and machine learning technique. The proposed method not only has good data mining ability, generalization ability and sound adaptivity to small samples, but also has the ability to improve the computational accuracy by reducing the effect of collinearity between logging curves. In prediction of two mud shale reservoirs of Sichuan basin with proposed model, the results showed that the predicted value of TOC was in good consistence with the measured value. The root-mean-square error of TOC predicting results was reduced from 0.415 (back-propagation neural networks) to 0.203 and 1.117 (back-propagation neural networks) to 0.357, respectively; the relative error value decreased by up to 8.9%. The Multiboost-KELM algorithm proposed in this paper can effectively improve the prediction accuracy of TOC in marine mud shale reservoir.

Relationship between seed size and plant abundance in an alpine meadow of the Qinghai-Tibetan Plateau

Liu B., Luo Y.

Polish Journal of Ecology

2009

Vol. 57, nr 3

573-579

Theoretical and field studies on seed size and plant abundance relationship have been conducted in various communities. However, inconsistent patterns have emerged from these studies, and still little is known about alpine meadows. Here we identified four models and their predictions: the seed size/number trade-off model (SSNTM), the succession model (SM), the spatial competition model (SCM), and the triangle model (TM), in order to assess the relationship between seed size and abundance in alpine meadows, and to elucidate underlying mechanisms. The study site was situated on the eastern Qinghai-Tibetan Plateau at 3500 m above sea level. From 1999 through 2001, two indices of plant abundance (aboveground biomass and density) were simultaneously measured in 45 quadrates (0.25 m[^2]). Data for 101 plant species (mostly Cyperaceae, Poaceae, Asteraceae, Ranunculaceae and forbs) showed that seed size is like log normal distributed, and it slightly skewed in smaller-sized seeds. The SSNTM, the TM, the SM and the SCM models were not supported in this alpine meadow, and the relationship between seed size and abundance was always positive (although in some samples, the relationship was not significant). The positive correlation between seed size and abundance observed for some grassland communities was also demonstrated in the alpine meadow. It suggests that seed size depends on the plant growth form, but the biomass-density relationship is inconsistent with previous studies. This suggests that the measure of abundance used in these studies is not the only reason for inconsistency of seed size.