Claim Missing Document
Check
Articles

Urban Air Quality Classification Using Machine Learning Approach to Enhance Environmental Monitoring Idroes, Ghazi Mauer; Noviandy, Teuku Rizky; Maulana, Aga; Zahriah, Zahriah; Suhendrayatna, Suhendrayatna; Suhartono, Eko; Khairan, Khairan; Kusumo, Fitranto; Helwani, Zuchra; Abd Rahman, Sunarti
Leuser Journal of Environmental Studies Vol. 1 No. 2 (2023): November 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ljes.v1i2.99

Abstract

Urban areas worldwide grapple with environmental challenges, notably air pollution. DKI Jakarta, Indonesia's capital city, is emblematic of this struggle, where rapid urbanization contributes to increased pollutants. This study employed the CatBoost machine learning algorithm, known for its resistance to overfitting and capability to handle missing data, to predict urban air quality based on pollutant levels from 2010 to 2021. The dataset, sourced from Jakarta's air quality monitoring stations, includes pollutants such as PM10, SO2, CO, O3, and NO2. After preprocessing, we used 80% of the data for training and 20% for testing. The model displayed high accuracy (0.9781), precision (0.9722), and recall (0.9728). The feature importance chart revealed O3 (Ozone) as the top influencer of air quality predictions, followed by PM10. Our findings highlight the dominant pollutants affecting urban air quality in Jakarta, Indonesia and emphasizing the need for targeted strategies to reduce their concentrations and ensure a cleaner and healthier urban environment.
Eco-Friendly Approach to Palm Oil Biodiesel Production: Torrefied Palm Frond Carbon as a Source for CaO/C/NaOH Catalysts Helwani, Zuchra; Amraini, Said Zul; Asmura, Jecky; Othman, Mohd. Roslee; Peliciamanuela, Samantha; Anggriani, Rara Dewi
Leuser Journal of Environmental Studies Vol. 2 No. 1 (2024): April 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ljes.v2i1.171

Abstract

Biomass-based sources for energy generation have attracted much attention recently due to its environmental benefits. These days, using edible oils and alkali catalysts, such as CaO, is standard practice for the transesterification step of the biodiesel synthesis process. Glycerine and methanol will form hydrogen bonds with the oxygen ions on the CaO surface, increasing the viscosity of the glycerine and causing CaO to suspend. Even though CaO was utilized directly as a catalyst in the transesterification process, extracting the CaO and glycerine from the final product will be challenging. To solve this issue, any extra metal oxides or catalyst supports ought to be impregnated into the CaO. This work has investigated the possible use of eggshells and palm fronds in developing bifunctional catalysts for biodiesel production. A series makes the processes' catalyst, including impregnation, calcination, and torrefaction. To assess the catalyst's performance, the esterification and transesterification of palm oil with a 2.9% free fatty acid content were investigated at a methanol/oil ratio of 6:1, catalyst concentration of 1-3% by weight, reaction temperature of 70 °C, and duration of 3 hours. The catalyst was found to have a specific surface area of 8.266 m2/g. There was an 89.4% yield of biodiesel produced. A viable, economical, and ecologically friendly method of producing biodiesel is to use eggshells and palm fronds in catalyst synthesis.
Ensemble Machine Learning Approach for Quantitative Structure Activity Relationship Based Drug Discovery: A Review Noviandy, Teuku Rizky; Maulana, Aga; Idroes, Ghazi Mauer; Emran, Talha Bin; Tallei, Trina Ekawati; Helwani, Zuchra; Idroes, Rinaldi
Infolitika Journal of Data Science Vol. 1 No. 1 (2023): September 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijds.v1i1.91

Abstract

This comprehensive review explores the pivotal role of ensemble machine learning techniques in Quantitative Structure-Activity Relationship (QSAR) modeling for drug discovery. It emphasizes the significance of accurate QSAR models in streamlining candidate compound selection and highlights how ensemble methods, including AdaBoost, Gradient Boosting, Random Forest, Extra Trees, XGBoost, LightGBM, and CatBoost, effectively address challenges such as overfitting and noisy data. The review presents recent applications of ensemble learning in both classification and regression tasks within QSAR, showcasing the exceptional predictive accuracy of these techniques across diverse datasets and target properties. It also discusses the key challenges and considerations in ensemble QSAR modeling, including data quality, model selection, computational resources, and overfitting. The review outlines future directions in ensemble QSAR modeling, including the integration of multi-modal data, explainability, handling imbalanced data, automation, and personalized medicine applications while emphasizing the need for ethical and regulatory guidelines in this evolving field.
Environmental Benefits of Palm Oil Biodiesel Enhancement: Urea Complexation Optimization via RSM Helwani, Zuchra; Amraini, Said Zul; Abd Rahman, Sunarti; Zahrina, Ida; Julhijah, Noni; Ulfaa, Suci Mas’ama
Leuser Journal of Environmental Studies Vol. 2 No. 2 (2024): October 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ljes.v2i2.214

Abstract

Indonesian commercial biodiesel products are unstable due to polyunsaturated fatty acids (PUFA). The urea inclusion compound (UIC) method is used during the fractionation process on PUFA to enhance its quality. This study aims to determine the effect of temperature, fatty acid ester metal (FAME)/methanol ratio, and crystallization time on increasing the concentration of PUFA concentrates and to produce high-performance biodiesel products with an iodine indicator <30–40 g I2/100 g. According to the most recent research, the UCF phase product is obtained at a combination of temperature and crystallization time of 20 °C and 4 h, respectively. It has an iodine number of 44.01 and an oxidation stability of 18.61 h, which is close to the criteria for high-performance biodiesel (<30 –40 g I2/100 g). Meanwhile, the results of this study obtained a UCF phase product that has an iodine number of 34.18 and yields 86.57% is obtained at a combination of temperature and crystallization time of 20 °C and 6 hr and FAME-methanol ratio of 6, respectively, which is close to the criteria for high-performance biodiesel (<30 –40 g I2/100 g). The longer complexation time and temperature significantly affected the FAME fractionation of the UCF phase.
Karakterisasi Biochar dari Tandan Kosong Kelapa Sawit Febrina, Wetri; Awaluddin, Amir; Saryono, Saryono; Helwani, Zuchra
JURNAL UNITEK Vol. 17 No. 2 (2024): Juli - Desember
Publisher : Sekolah Tinggi Teknologi Dumai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52072/unitek.v17i2.1150

Abstract

Pada awalnya teknologi biochar berkembang pesat karena manfaatnya dalam meningkatkan kesuburan tanah, memperbaiki struktur tanah, meningkatkan hasil panen dan memperbaiki kondisi tanaman.. Penggunaan biochar saat ini meluas diluar bidang pertanian, diantaranya sebagai bahan bakar alternatif, dan sebagai adsorben dalam pengolahan air limbah. Pemanfaatan limbah pertanian dan perkebunan menjadikan pemanfaatan biochar bermanfaat dalam usaha untuk memperbaiki kondisi lingkungan.  Penelitian ini bertujuan untuk mengetahui dan menganalisis karaktersitik fisikokimia biochar dari tandan kosong kelapa sawit, dan potensinya sebagai adsorben pengolahan limbah cair.  Biochar diaktifkan menggunakan kalium hidroksida (KOH) pada berbagai konsentrasi. EFB yang diaktivasi dengan KOH 3M menunjukkan kapasitas adsorpsi tertinggi dibandingkan dengan yang diaktivasi dengan KOH 2M dan 1M. Hasil ini didukung oleh data tentang gugus fungsi dan struktur pori, yang diamati menggunakan spektroskopi Fourier Transform Infrared (FTIR) dan metode Brunauer-Emmett-Teller (BET).
Esterifikasi dan Transesterifikasi Minyak Kelapa Sawit Off-grade Menjadi Biodiesel Menggunakan Katalis Barium Hidroksida Nurfatihayati; Helwani, Zuchra; Bahri, Syaiful
Jurnal Teknik Kimia USU Vol. 14 No. 1 (2025): Jurnal Teknik Kimia USU
Publisher : Talenta Publisher (Universitas Sumatera Utara)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jtk.v14i1.17736

Abstract

This research aimed to produce biodiesel from off-grade palm oil using barium hydroxide (Ba(OH)2) catalyst. The free fatty acid (FFA) content in off-grade palm oil is quite high, so the biodiesel production process is carried out in two-stages, i.e. esterification and transesterification. The esterification of off-grade palm oil (500 mL) was carried out at 60 oC for 1 hour, methanol:oil molar ratio of 12:1, stirrer speed of 400 rpm, and 1 wt-% sulfuric acid (H2SO4) as the catalyst. Next, the transesterification process used a methanol:oil molar ratio of 9:1, stirrer speed of 400 rpm, for 2 hours with the variation of temperatures (50, 60, and 70 oC) and Ba(OH)2 catalyst amounts (1, 2 and 3 wt-%). The best result was obtained with 60 oC and Ba(OH)2 catalyst amount 3 wt-%. Based on Gas Chromatography-Mass Spectroscopy (GC-MS) analysis, the best yield of fatty acid methyl ester was 98.97%, with major components being 40.87% palmitic acid and 35.87% oleic acid. The characteristics of biodiesel produced were density of 860.46 kg/m3, viscosity of 4.08 mm/s2, flash point of 145 oC and acid value of 0.457 mg KOH/g biodiesel.
Esterifikasi dan Transesterifikasi Minyak Kelapa Sawit Off-grade Menjadi Biodiesel Menggunakan Katalis Barium Hidroksida Nurfatihayati; Helwani, Zuchra; Bahri, Syaiful
Jurnal Teknik Kimia USU Vol. 14 No. 1 (2025): Jurnal Teknik Kimia USU
Publisher : Talenta Publisher (Universitas Sumatera Utara)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jtk.v14i1.17736

Abstract

This research aimed to produce biodiesel from off-grade palm oil using barium hydroxide (Ba(OH)2) catalyst. The free fatty acid (FFA) content in off-grade palm oil is quite high, so the biodiesel production process is carried out in two-stages, i.e. esterification and transesterification. The esterification of off-grade palm oil (500 mL) was carried out at 60 oC for 1 hour, methanol:oil molar ratio of 12:1, stirrer speed of 400 rpm, and 1 wt-% sulfuric acid (H2SO4) as the catalyst. Next, the transesterification process used a methanol:oil molar ratio of 9:1, stirrer speed of 400 rpm, for 2 hours with the variation of temperatures (50, 60, and 70 oC) and Ba(OH)2 catalyst amounts (1, 2 and 3 wt-%). The best result was obtained with 60 oC and Ba(OH)2 catalyst amount 3 wt-%. Based on Gas Chromatography-Mass Spectroscopy (GC-MS) analysis, the best yield of fatty acid methyl ester was 98.97%, with major components being 40.87% palmitic acid and 35.87% oleic acid. The characteristics of biodiesel produced were density of 860.46 kg/m3, viscosity of 4.08 mm/s2, flash point of 145 oC and acid value of 0.457 mg KOH/g biodiesel.
Synthesis of biochar from fronds palm waste as a support for CaO catalyst Oktariandi, Vito; Helwani, Zuchra; Akbar, Irfan Sarhadi; Rizky, Muhammad Dian; Anjani, Putri; Perdana, Rendy Putra; Amri, Amun
Konversi Vol 13, No 2 (2024): OKTOBER 2024
Publisher : Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/k.v13i2.20242

Abstract

Production palm oil-based biodiesel production itself has been widely developed in Indonesia to replace fuel because the palm oil commodity has the greatest potential for biodiesel for biodiesel production. The use of catalysts affects the production of biodiesel because it can accelerate the production of biodiesel which is needed. Materials that has the potential to be part of the catalyst is activated carbon from palm frond waste palm. Palm frond waste has great potential and is supported by its lignocellulosic component. lignocellulose component, so it can be utilized as activated carbon. Research This research has variations in the procedure, namely pyrolysis temperature variations of 450°C and 500°C, pyrolysis time of 15 minutes and 20 minutes as well as the base used in impregnation, namely NaOH and KOH. The catalyst that has been The synthesized catalyst was characterized using XRD and BET analysis. XRD testing XRD testing obtained the smallest particle size on the 500°C CaO/NaOH/Biochar catalyst with a pyrolysis time of 15 minutes amounting to 26.925732 nm and in the BET test, the smallest particle size was obtained. BET testing obtained the largest catalyst surface area on CaO/NaOH/Biochar catalyst 500°C with pyrolysis time of 15 minutes amounted to 8.1626 m2/g.
Improving the Environmental Performance of Palm Biodiesel via AgNO₃-Assisted Removal of Polyunsaturated Fatty Acids Helwani, Zuchra; Zahrina, Ida; Amraini, Said Zul; Idroes, Rinaldi; Neonufa, Godlief Frederick; Rahman, Sunarti Abd
Leuser Journal of Environmental Studies Vol. 3 No. 1 (2025): April 2025
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ljes.v3i1.274

Abstract

Indonesian biodiesel products commonly exhibit low oxidative stability and high cloud points, which limit their performance and widespread use. These drawbacks are primarily due to the high content of polyunsaturated fatty acids (PUFAs) in the fatty acid methyl ester (FAME) mixture that constitutes biodiesel. A more suitable biodiesel composition includes higher proportions of saturated and monounsaturated fatty acids, which offer better combustion properties, higher cetane numbers, and greater resistance to oxidative degradation. In contrast, PUFAs promote oxidation reactions, resulting in fuel instability, increased sludge formation, and higher emissions of unburned hydrocarbons, negatively impacting both engine performance and the environment.This study investigates the use of silver nitrate (AgNO₃) as a selective extraction agent to remove PUFAs from palm oil-derived FAME. The goal is to identify the most effective biodiesel-to-AgNO₃ volume ratio for separating saturated fatty acid fractions from unsaturated ones, in order to produce a more stable and environmentally friendly biodiesel. Experimental results show that a 1:2 volume ratio significantly reduces the iodine number, from 57.22 to 47.38 g I₂/100 g sample, indicating a decrease in unsaturated compounds. Furthermore, oxidative stability improved from 11.18 hours to 11.69 hours after extraction. The removal of PUFAs not only improves the fuel's storage and combustion stability but also enhances its environmental profile. More stable biodiesel burns more completely, reducing emissions of particulate matter and greenhouse gases, and contributing to cleaner air and lower environmental impact. Thus, PUFA extraction using AgNO₃ presents a promising approach for improving the sustainability and performance of palm-based biodiesel fuels.
Inductive Biases in Feature Reduction for QSAR: SHAP vs. Autoencoders Noviandy, Teuku Rizky; Idroes, Ghifari Maulana; Lala, Andi; Helwani, Zuchra; Idroes, Rinaldi
Infolitika Journal of Data Science Vol. 3 No. 1 (2025): May 2025
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijds.v3i1.306

Abstract

Machine learning models in drug discovery often depend on high-dimensional molecular descriptors, many of which may be redundant or irrelevant. Reducing these descriptors is essential for improving model performance, interpretability, and computational efficiency. This study compares two widely used reduction strategies: SHAP-based feature selection and autoencoder-based compression, within the context of Quantitative Structure-Activity Relationship (QSAR) classification. LightGBM is used as a consistent modeling framework to evaluate models trained on all descriptors, the top 50 and 100 SHAP-ranked descriptors, and a 64-dimensional autoencoder embedding. The results show that SHAP-based selection produces interpretable and stable models with minimal performance loss, particularly when using the top 100 descriptors. In contrast, the autoencoder achieves the highest test performance by capturing nonlinear patterns in a compact, low-dimensional representation, although this comes at the cost of interpretability and consistency across data splits. These findings reflect the differing inductive biases of each method. SHAP prioritizes sparsity and attribution, while autoencoders focus on reconstruction and continuity. The analysis emphasizes that descriptor reduction strategies are not interchangeable. SHAP-based selection is suitable for applications where interpretability and reliability are essential, such as in hypothesis-driven or regulatory settings. Autoencoders are more appropriate for performance-driven tasks, including virtual screening. The choice of reduction strategy should be guided not only by performance metrics but also by the specific modeling requirements and assumptions relevant to cheminformatics workflows.
Co-Authors Abd , Ammar Ali Abd Rahman, Sunarti Afriyenti, Mia Agustiyanti, Rini Dwi Agustiyanti, Rini Dwi Ahmad Fadli Ahmad, Khairunnas Akbar, Irfan Sarhadi Amir Awaluddin Amun Amri Anggraini, Diva Putri Anggriani, Rara Dewi Anjani, Putri Anuar, Kaspul Asep Rusyana Aswie, Viqha Bahruddin Bahruddin Bahruddin Boy M. Bachtiar Damayanti, Elok David Andrio Dhani Nur Miftahudin Dizikri, Dizikri Drastinawati Drastinawati Drastinawati Drastinawati, Drastinawati Dwi Septiana Edi Susanto Edy Saputra Eko Suhartono Emran, Talha Bin Febrina Dwi Putri Febrina Dwi Putri, Febrina Dwi Febrina, Wetri Fernando, Rivo Ghazi Mauer Idroes Hafiz, Fadlillahi Hanafi, Muhammad Rifter Hari Rionaldo Hari Rionaldo Hawa, Karfika Ainil Hawa, Karfika Ainil Hutagaol, Martiandes Ida Zahrina Idral Amri Idroes, Ghazi M. Idroes, Ghifari Maulana Jecky Asmura Julhijah, Noni Karfika Ainil Hawa Karina Octaria Putri Kemala, Pati Kesni Savitri Khairan Khairan Komalasari Komalasari Komang, Hendri Kusumo, Fitranto Lala, Andi Lubis, Vanizra F. Lukman Arifin Maulana, Aga Maulydia, Nur B. Miftahudin, Dhani Nur Miftahudin, Dhani Nur Muhammad Mardhiansyah Muhammad Zen, Muhammad Muliadi Ramli Mulya, Dynna Ardilla Putri Muslim Abdurrahman, Muslim Nasution, Muhammad Hatta Nazaris, Nazsha Nayyazsha Neonufa, Godlief Frederick Ningsih, Diana S. Noviandy, Teuku R. Nurfatihayati Nurwijayanti Oktariandi, Vito Oktriyono, Febri Dwi Olsy, Fradilla Othman, Mohd. Roslee Peliciamanuela, Samantha Perdana, Rendy Putra Prasetyo Arva S, Prasetyo Arva Pratama, Teddy Pratama, Yudistira Putra Zelly Nugraha, Putra Zelly Putra, Bayu Eldino Putra, Yogi Lesmana Putri, Karina Octaria Putri, Karina Octaria Qalbi, Tiffani Rafi, M Khaidiz Rahayu, Ricky Puji Rahman, Sunarti Abd Raja Heru Nur Alam Ichsan, Raja Heru Nur Alam Randi Sanjaya Randi Sanjaya, Randi Reno Susanto Reski, M. Rinaldi Idroes Rizki, Juliana Rizky, Muhammad Dian Rozanna Sri Irianty Saparullah, Zulkarnaen Saryono Saryono Setiadi, Fydel Simbolon, Kristin Madelin Siregar, Thasya Nurfadillah Sitorus, Mesakh Fridolin Sugesti, Heni Suhendrayatna Suhendrayatna Sunarno Sunarno Surya, Andry Pratama Susanty, Wenny Susilowati Susilowati Syafi’i, Abdullah Syahputra, Dede SYAIFUL BAHRI Tengku Mukhlis Teuku Rizky Noviandy Topan Herianto Trina E. Tallei, Trina E. TRINA EKAWATI TALLEI Triwahyuni, Vanny Efia Ulfaa, Suci Mas’ama Ulima, Riris Warman Fatra, Warman Wenny Susanty Yelmida Azis Yemita, Sylvia Yudha, Ricky Satria Z Zulfansyah Zahriah, Zahriah Zohera, Zohera Zul Amraini, Said Zulfansyah Zulfansyah Zultiniar, Zultiniar