A Study on Spatial and Temporal Dynamic Changes of Desertification in Northern China from 2000 to 2020

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(5), P. 1368 - 1368

Published: Feb. 28, 2023

Desertification is of significant concern as one the world’s most serious ecological and environmental problems. China has made great achievements in afforestation desertification control recent years. The climate varies greatly across northern China. Using a long-time series remote sensing data to study effects will further understanding China’s engineering change mechanisms. moist index was employed this research determine type delineate potential occurrence range Then, based on Google Earth Engine platform, MODIS were used construct various monitoring indicators applied four machine learning models. By comparing different combinations models, it concluded that random forest model with indicator had highest accuracy 86.94% Kappa coefficient 0.84. Therefore, monitor area from 2000 2020. According our studies, decreased by more than 237,844 km2 between 2020 due impact human activities addition climatic factors such important role precipitation. This gives database for cause well reference national-scale monitoring.

Language: Английский

---

Recent trends in computational intelligence for educational big data analysis

Iran Journal of Computer Science, Journal Year: 2023, Volume and Issue: 7(1), P. 103 - 129

Published: Sept. 7, 2023

Language: Английский

---

Tolerance traits related to climate change resilience are independent and polygenic

Global Change Biology, Journal Year: 2018, Volume and Issue: 24(11), P. 5348 - 5360

Published: July 11, 2018

Abstract The resilience of organisms to climate change through adaptive evolution is dependent on the extent genetically based variation in key phenotypic traits and nature genetic associations between them. For aquatic animals, upper thermal tolerance hypoxia are likely be a important determinants sensitivity change. To determine basis these detect them, we compared naturally occurring populations two subspecies Atlantic killifish, Fundulus heteroclitus , that differ both tolerance. Multilocus association mapping demonstrated 47 35 single nucleotide polymorphisms (SNPs) explained 43.4% 51.9% tolerance, respectively, suggesting mechanisms underlie substantial proportion each trait. However, no explanatory SNPs were shared traits, varied approximately linearly with latitude, whereas exhibited steep break across contact zone subspecies. These results suggest neither phenotypically correlated nor associated, thus rates can independently fine‐tuned by natural selection. This modularity underpin evolvability complex future environmental

Language: Английский

---

The use of classification and regression algorithms using the random forests method with presence-only data to model species’ distribution

MethodsX, Journal Year: 2019, Volume and Issue: 6, P. 2281 - 2292

Published: Jan. 1, 2019

Random forests (RF) is a powerful species distribution model (SDM) algorithm. This ensemble by default can produce categorical and numerical maps based on its classification tree (CT) regression (RT) algorithms, respectively. The CT algorithm also predictions (class probability). Here, we present detailed procedure involving the use of RT algorithms using RF method with presence-only data to species. are used generate prediction maps, then converted binary through objective threshold-setting methods. We applied simple methods deal collinearity predictor variables spatial autocorrelation occurrence data. A geographically stratified sampling was employed for generating pseudo-absences. procedural framework meant be generic virtually any SDM question •How as standard distributions data•How choose (CT or RT) modeling species•A general question.

Language: Английский

---

The genetic basis of spatial cognitive variation in a food-caching bird

Current Biology, Journal Year: 2021, Volume and Issue: 32(1), P. 210 - 219.e4

Published: Nov. 3, 2021

Language: Английский

---