Yudaputra A, Pujiastuti I, Cropper Jr. WP. 2019. Comparing six different species distribution models with several subsets of environmental variables: predicting the potential current distribution of zebra Guettarda speciosa in Indonesia. Biodiversitas 20: 2321-2328. There are many algorithms of species distribution modeling that widely used to predict the potential distribution pattern of diverse organisms. Finding the best model in terms of predicting the potential distribution of many species remains a challenge. The objective of this study is to compare six different algorithms for predicting the potential current distribution pattern of Guettarda speciosa (zebra wood). The occurrence records of G. speciosa are derived from herbarium database, Bogor Botanic Gardens’s plant inventory database and direct field surveys through NKRI expedition. Seven climatic variables and elevation data are extracted from global data. R open-source software is used to run those algorithms and QGIS is used to prepare the spatial data. The result shows that MAXENT outperforms other predictive models with the highest AUC score 0.89, followed by SVM (0.87), RF (0.86), and GLM (0.82), DOMAIN (0.73), and BIOCLIM (0.62). Based on the AUC score, the four predictive models (MAXENT, SVM, RF, GLM) are categorized into good predictive models, indicating those are quite better to predict the potential current distribution pattern of G. speciosa. Whereas, DOMAIN is fair predictive model and BIOCLIM is poor predictive model. The predictive map derived from four models (MAXENT, SVM, RF, and GLM) shows almost similar appearance in predicting of potential current distribution of G. speciosa. The predictive map of current distribution would be useful to provide information regarding the potential habitat of G. speciosa across the landscape of Indonesia.
The conservation of species should be based on knowledge of habitat requirements, population structure and conservation status. This knowledge is quite important to design conservation areas for species and to promote long-term persistence. In this study, we investigated habitat suitability, population size structure and conservation status of Pinanga arinasae in Bali. Plots with palms and adjacent areas with no palms were sampled to characterize key habitat variables. Habitat suitability was modeled using Artificial Neural Network (ANN) and Random Forest (RF) methods. The population size structure was characterized by counting and measuring the height and reproductive status of the individuals found in plots. Furthermore, we assessed the extinction risk of the species using the IUCN Red List Criteria. The ANN variables that best explained occurrence were litter depth, elevation, canopy openness and slope. The RF variables that best explained the data were elevation, litter depth, slope, and aspect. Both ANN and RF are robust models that can be used to predict the occurrence of P. arinasae. The population size structure included many seedlings, but juvenile and mature individuals were found in relatively small numbers. Based on the findings, we proposed Endangered B1+B2ab(i,ii,iii,v); D as the conservation status of P. arinasae.
5 December 2019 in Biodiversitas Journal of Biological Diversity
Yudaputra A, Fijridiyanto I, Cropper WPJr. 2020. The potential impact of climate change on the distribution pattern of Eusideroxylon zwageri (Bornean Ironwood) in Kalimantan, Indonesia. Biodiversitas 21: 326-333. Eusideroxylon zwageri Teijsm & Binn. is a vulnerable tree species with considerable economic value. The high demand for its wood makes this species vulnerable. Population vulnerabilities of E. zwageri include habitat loss, land-use change, and forest encroachment. An additional potential risk factor is climate change, with a possible increase in temperature of about 2.5 to 10 degrees Fahrenheit over the next century. Climate is considered to be a principal factor that determines the distribution of many species. This study addresses the potential current and future distribution of E. zwageri under climate change. Seven predictor climate variables are selected from 19 climatic variables using VIF (Variance Inflation Factor) to eliminate multicollinearity among variables. The spatial data is prepared using Geographic Information System (GIS). Six species distribution models (RF, SVM, MARS, GAM, GLM) and the ensemble model are applied to understand the potential current geographical distribution of E. zwageri. For risk assessment, the potential future distribution is predicted using the ensemble model only. All models are run using R open-source software. In model evaluation, all models have AUC value >0.80, indicating those models are good predictive models. All predictive models have the TSS >0.60 which means those models having a useful agreement between prediction and real observation. Precipitation seasonality, isothermality, and precipitation of the coldest quarter are the most important model variables that influence the current and future distribution of E. zwageri. Four models (RF, SVM, GAM, GLM) produce similar predictive maps of potential current distribution. MARS produces a slightly different predictive map. The future projection of ensemble model shows that the distribution area is more likely shifted and decreased from the current to 2050 and 2070.
29 May 2021 in Annual Research & Review in Biology
Aims: This study aims to predict the future geographic distribution shift of invasive plant species Austroeupathorium inulifolium as the impact of global climate change. Study Design: The rising temperature and precipitation change lead to the geographic distribution shift of organisms. A. inulifolium belongs to invasive plant species that often causes a substantial economic loss and ecological degradation in the invaded areas. Modelling of species distribution using the climate-based model could be used to understand the geographic distribution shift of invasive species in the future scenario under global climate change. Place and Duration of Study: Center for Plant Conservation and Botanic Gardens – LIPI and 6 months. Methodology: The total 2228 of occurrence records were derived from the Global Biodiversity Information Facility (GBIF) database. The seven climatic variables were selected from 19 variables using a pairwise correlation test (vifcor) with a threshold >0.7. The ensemble model was used by combining Random Forest (RF) and Support Vector Machine (SVM). Results: Both two models are well-performed either using AUC or TSS evaluation methods. RF and SVM have AUC >0.95, and TSS >0.8. The predicted current distribution tends to have larger distribution areas compared to observed occurrence records. The predicted future distribution seems to be shifted in several parts of North America and Europe. Conclusion: The geographic distribution of invasive plant species A. inulifolium will be shifted to the Northern part of globe in 2090. Mean temperature of driest quarter and precipitation of warmest quarter are the two most important variables that determine the distribution pattern of the A. inulifolium. The predictive distribution pattern of invasive plant A. inulifolium would be important to provide information about the impact of climate change to the geographic distribution shift of this species.
29 June 2024 in Buitenzorg: Journal of Tropical Science
Pinanga javana Blume yang terdaftar dalam daftar merah IUCN, juga dikenal sebagai Pinang Jawa, sebagai spesies yang dilindungi dan terancam punah yang endemik di pulau Jawa, Indonesia. Penelitian ini fokus mempelajari proses perkecambahan dan pertumbuhan bibit P. javana dengan menggunakan empat jenis media tanam yaitu cocopeat, sekam, pasir, dan serbuk gergaji. Hasil penelitian menunjukkan kadar air biji P. javana perlahan menurun dari 33,96% menjadi 24,45% selama masa penyimpanan hari ke-0 hingga hari ke-21. Media tanam mempunyai pengaruh yang nyata terhadap laju perkecambahan, pasir mempunyai nilai tertinggi (2,34). dan sekam memberikan pertumbuhan bibit terbaik. Cocopeat memiliki tingkat kelembapan tertinggi (90%), sedangkan pasir menghasilkan tingkat kelembapan terendah. PH semua media berada dalam kisaran normal (6-7) yang mendukung perkecambahan optimal. Analisis berbagai parameter menyimpulkan bahwa pasir merupakan media tanam yang optimal bagi P. javana dalam penelitian ini. Kata Kunci: perkecambahan, media tanam, Pinanga javana, viabilitas, kadar air