Using Machine Learning to Model Future Distributions of Babandotan Ageratum conyzoides L. Under Climate Change Scenarios (CMIP 5: RCP 2.6 and RCP 8.5) until 2070 in Bandung Areas

Aug 5, 2026

Ageratum conyzoides L. (Babandotan), valued in West Java for medicinal uses, is sensitive to climate-driven habitat change. This study applies machine learning species distribution modeling to project future distributions in Bandung and surrounding areas under CMIP5 climate change scenarios RCP 2.6 and RCP 8.5 up to 2070. Occurrence records are sampled from nine locations, modeled with MaxEnt using the R platform, and evaluated with AUC. Current suitable habitat covers about 1250 km² and shows strong model performance (AUC 0.964). Under climate scenarios, suitability shifts northward and declines in southern Bandung by 2070.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Keywords

1. Introduction

Background of Ageratum conyzoides in West Java

Species distribution modeling and climate scenarios

e-ISSN: 2655-8777 [http://journals.itb.ac.id/index.php/3bio](http://journals.itb.ac.id/index.php/3bio) Using Machine Learning to Model Future Distributions of BabandotanAgeratum conyzoides L. Under Climate Change Scenarios (CMIP 5: RCP 2.6 and RCP 8.5) until 2070 in Bandung Areas Andriwibowo1*, Vita Meylani2 1) School of Environmental Science, Universitas Indonesia, Jakarta, Indonesia 2) Biology Education Department, Faculty of Teaching and Education Science, Universitas Siliwangi, Tasikmalaya 46115 Indonesia *) Corresponding author; e-mail: [adiwibowoecol@yahoo.com](adiwibowoecol@yahoo.com) [Received: 2024-02-11](Received: 2024-02-11) Accepted for publication: 2025-07-17 Abstract Ageratum conyzoides L., locally known as Babandotan, is an important plant in particular in West Java, including in Bandung, due to its medicinal uses. Currently, climate change is known to influence the distribution of organisms by altering climates and making habitats suitable or not suitable. Then, this present study is aiming to use machine learning to model future distributions of A. conyzoides under climate change scenarios CMIP 5 RCP 8.5 until 2070 in Bandung areas. The A. conyzoides occurrences were sampled from nine locations in Bandung and its surrounding areas. Machine learning using the R platform and MaxEnt algorithm was used to develop species distribution modeling (SDM) . The model was then simulated using RCP 2.6 and 8.5 scenarios for the years 2050 and 2070. The quality of the model was assessed using AUC values. The current SDM model shows suitable habitats for A. conyzoides are sizing 1250 km2, mostly located in Bandung (56%), Kota Bandung (24%), and Sumedang (16%) . The AUC value was 0.964, showing that the resulting model is good. Climate change will affect A. conyzoides in the future. Based on the RCP model, suitable habitats forA. conyzoides will be shifted northward, eliminating the suitable habitats in the south of Bandung, as can be seen in 2070. Keywords: AUC, Babandotan, RCP, suitable 1. Introduction Ageratum conyzoides or locally known as Bandotanor Wedusan is a type of agricultural weed belonging to the Asteraceae family [1] . This annual herb originates from tropical America, especially Brazil, but has long been introduced and wild in the archipelago. In Indonesia, this species has various local names according to its locality. In West Java, it is called as Babandotan or Babadotan; in most of Java Island, it is called as Wedusan; in Madura Island, it is called as Dus-Bedusan; and Rumput Balam in Pontianak, West Kalimantan Island. While in english name, A. conyzoides is known as Billygoat weed, Goat weed [2, 3], Chick weed, or White weed. This species plant acquires its name because the smell odor it emits resembles the smell odor of a goat. This plant is widespread throughout tropical regions, even to the subtropics. Imported to Java before 1860, now this weed has spread widely in Indonesia. In South America, this plant is even cultivated. This plant is often found as a nuisance plant in dry rice fields, fields, yards, roadsides, embankments, water edges, and bushy areas. This plant is found up to an altitude of 3,000 m, this herb flowers all year round and can produce up to 40,000 seeds per individual plant. In West Java, this species is widely use as medicinal plants for particular wound remedy [4] . Recently, large scale patterns of species distribution including plants and medicinal plants were impacted by climate change and greenhouse gas concentration determines. Intergovernmental Panel on Climate Change (IPCC) has created several climate scenarios based on greenhouse gas concentrations known as Representative Concentration Pathways (RCP) . RCP 8.5 is an emission scenario without policies to reduce emissions with a rapid increase in methane, high use of fossil fuels, and the slow development of technology to reduce the impact of climate change. Then, RCP 8.5 climate scenario is consi

FAQs

Why is Ageratum conyzoides (Babandotan) important in the study area?

It is an important plant in West Java, including Bandung, partly because of its medicinal uses and local presence.

Which machine learning method and platform are used to model future distributions?

The study uses MaxEnt with machine learning implemented through the R platform to develop species distribution modeling (SDM).

How does climate change affect suitable habitat by 2070?

The modeled suitable habitats shift northward, with suitable conditions eliminated in the south of Bandung by 2070.

Aug 5, 2026

Upload by Genevieve