Robotics & Machine Learning Daily News2024,Issue(Jun.7) :81-81.

Studies from Gadjah Mada University Reveal New Findings on Machine Learning (Imp act of landslide on geoheritage: Opportunities through integration, geomorpholog ical classification and machine learning)

Gadjah Mada大学的研究揭示了机器学习的新发现(滑坡对地质遗产的影响:整合、地貌分类和机器学习带来的机遇)

Robotics & Machine Learning Daily News2024,Issue(Jun.7) :81-81.

Studies from Gadjah Mada University Reveal New Findings on Machine Learning (Imp act of landslide on geoheritage: Opportunities through integration, geomorpholog ical classification and machine learning)

Gadjah Mada大学的研究揭示了机器学习的新发现(滑坡对地质遗产的影响:整合、地貌分类和机器学习带来的机遇)

扫码查看

摘要

由机器人与机器学习每日新闻的新闻记者兼工作人员新闻编辑-人工智能的新数据在一份新的报告中呈现。根据NewsRx记者来自印度尼西亚Yogy Akarta的新闻报道,研究表明:“人们普遍认为滑坡会对地质特征和周围环境造成破坏。我们的研究重点是Karangsambung-Karang Bolong地质公园(KKNG)北部地区,该地区岩性多样,构造多期。”新闻记者从Gadjah Mada大学的研究中获得了一句话:“这项研究的目的是探索(i)滑坡敏感性评估,(ii)滑坡敏感性的地貌特征和分布,以及(iii)滑坡对地质场所的影响。我们绘制了地貌形态、形态、材料和过程图,以了解地貌内容,确定了三种主要地貌:结构地貌、山麓地貌和河流地貌。F或滑坡敏感性图。”本文采用了XGBoost算法,并利用接收器工作特征曲线(AUROC)下的面积进行模型验证。XGBoost模型揭示了10个地质点的高敏感性分类。滑坡具有负面影响,如珊瑚灰岩的滑石、硅质岩的外来块和石灰性红粘土岩,改变地貌,破坏露头。然而,一些滑坡对地质点有积极影响。例如千枚岩的外来块,枕状熔岩和放射虫硅质岩的外来块,因为山体滑坡可以揭示出露头和岩石结构,露头面积也变大。陆地卫星测绘成功地识别出了非常脆弱和具有不利影响的地质点。将灾害视为一种有害过程的研究已经发展成为一种更具整体性的灾害观。

Abstract

By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on artificial intelligence are presented in a new report. According to news reporting originating from Yogy akarta, Indonesia, by NewsRx correspondents, research stated, “Landslides are wi dely understood to cause damage to the geological features and the surrounding e nvironment. Our study focuses on the northern region of the Karangsambung-Karang bolong Geopark (KKNG), characterized by diverse lithology and multi-phase tecton ics.” The news correspondents obtained a quote from the research from Gadjah Mada Univ ersity: “This study aims to explore (i) landslide susceptibility assessment, (ii ) geomorphological characteristics and distribution of landslide susceptibility, and (iii) identification of landslide impacts on geosites. We mapped morphogene sis, morphology, materials, and processes to understand the geomorphological con text, identifying three primary landforms: structural, pediments, and fluvial. F or landslide susceptibility mapping, we used the XGBoost algorithm with cross-va lidation and utilized the area under the receiver operating characteristic curve (AUROC) for model validation. The XGBoost model revealed a high susceptibility classification for 10 geosite points. Landslides have negative impacts, such as Olistoliths of coral limestones, Exotic-blocks of chert, and calcareous red clay stone that change landforms and damage outcrops. Nevertheless, some landslides h ave positive impacts on the geosite, such as Exotic-blocks of phyllites, and Exo tic-blocks of pillow lava and radiolarian chert, because landslides can reveal f resher outcrops and rock structures, and the outcrop area becomes larger. Landsl ide mapping successfully identified geosites that are highly vulnerable and have adverse impacts, especially those with certain lithological characteristics. Th is research on viewing disaster as a harmful process has evolved into a more hol istic view of the disaster.”

Key words

Gadjah Mada University/Yogyakarta/Indo nesia/Asia/Cyborgs/Emerging Technologies/Machine Learning

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文