Janani Venkatraman Jagatha

Ms. Janani Venkatraman Jagatha

Humboldt Universität zu Berlin
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 June 2021 in Sensors
Verified
Journal Article
Open access
PDF file
JJJanani Venkatraman Jagatha
Janani Venkatraman Jagatha
AKAndré Klausnitzer
André Klausnitzer
MCMiriam Chacón-Mateos
Miriam Chacón-Mateos
BLBernd Laquai
Bernd Laquai
ENEvert Nieuwkoop
Evert Nieuwkoop
CSChristoph Schneider
Christoph Schneider
Over the last decade, manufacturers have come forth with cost-effective sensors for measuring ambient and indoor particulate matter concentration. What these sensors make up for in cost efficiency, they lack in reliability of the measured data due to their sensitivities to temperature and relative humidity. These weaknesses are especially evident when it comes to portable or mobile measurement setups. In recent years many studies have been conducted to assess the possibilities and limitations of these sensors, however mostly restricted to stationary measurements. This study reviews the published literature until 2020 on cost-effective sensors, summarizes the recommendations of experts in the field based on their experiences, and outlines the quantile-mapping methodology to calibrate low-cost sensors in mobile applications. Compared to the commonly used linear regression method, quantile mapping retains the spatial characteristics of the measurements, although a common correction factor cannot be determined. We conclude that quantile mapping can be a useful calibration methodology for mobile measurements given a well-elaborated measurement plan assures providing the necessary data.

14 September 2022 in Environmental Science: Atmospheres
Verified
Journal Article
Open access
PDF file
ACAlexandre Caseiro
Alexandre Caseiro
SSSean Schmitz
Sean Schmitz
GVGuillermo Villena
Guillermo Villena
JJJanani Venkatraman Jagatha
Janani Venkatraman Jagatha
ESErika von Schneidemesser
Erika von Schneidemesser
Using low-cost systems to obtain indicative measurements when no calibration is possible.

27 June 2024 in Sensors
Verified
Journal Article
Open access
PDF file
JJJanani Venkatraman Jagatha
Janani Venkatraman Jagatha
CSChristoph Schneider
Christoph Schneider
TSTobias Sauter
Tobias Sauter
Machine learning (ML) methods are widely used in particulate matter prediction modelling, especially through use of air quality sensor data. Despite their advantages, these methods’ black-box nature obscures the understanding of how a prediction has been made. Major issues with these types of models include the data quality and computational intensity. In this study, we employed feature selection methods using recursive feature elimination and global sensitivity analysis for a random-forest (RF)-based land-use regression model developed for the city of Berlin, Germany. Land-use-based predictors, including local climate zones, leaf area index, daily traffic volume, population density, building types, building heights, and street types were used to create a baseline RF model. Five additional models, three using recursive feature elimination method and two using a Sobol-based global sensitivity analysis (GSA), were implemented, and their performance was compared against that of the baseline RF model. The predictors that had a large effect on the prediction as determined using both the methods are discussed. Through feature elimination, the number of predictors were reduced from 220 in the baseline model to eight in the parsimonious models without sacrificing model performance. The model metrics were compared, which showed that the parsimonious_GSA-based model performs better than does the baseline model and reduces the mean absolute error (MAE) from 8.69 µg/m3 to 3.6 µg/m3 and the root mean squared error (RMSE) from 9.86 µg/m3 to 4.23 µg/m3 when applying the trained model to reference station data. The better performance of the GSA_parsimonious model is made possible by the curtailment of the uncertainties propagated through the model via the reduction of multicollinear and redundant predictors. The parsimonious model validated against reference stations was able to predict the PM2.5 concentrations with an MAE of less than 5 µg/m3 for 10 out of 12 locations. The GSA_parsimonious performed best in all model metrics and improved the R2 from 3% in the baseline model to 17%. However, the predictions exhibited a degree of uncertainty, making it unreliable for regional scale modelling. The GSA_parsimonious model can nevertheless be adapted to local scales to highlight the land-use parameters that are indicative of PM2.5 concentrations in Berlin. Overall, population density, leaf area index, and traffic volume are the major predictors of PM2.5, while building type and local climate zones are the less significant predictors. Feature selection based on sensitivity analysis has a large impact on the model performance. Optimising models through sensitivity analysis can enhance the interpretability of the model dynamics and potentially reduce computational costs and time when modelling is performed for larger areas.

15 May 2023
Verified
Conference Paper
Open access
JJJanani Venkatraman Jagatha
Janani Venkatraman Jagatha
TSTobias Sauter
Tobias Sauter
CSChristoph Schneider
Christoph Schneider
Urban climate research is primarily based on point or location-based measurements of climate and air quality data. Advances in microsensor technologies and low cost due to production facilities, sensors for measuring air quality have spread to a large scale in the last decade. In contrast to reference devices, sensors are simple in design, lightweight, and easier to deploy in larger scales.United Nations environment programme regards Air pollution to be a major global health concern that causes one in nine deaths worldwide. Although a number of sources and factors have been identified as a cause of air pollution it is difficult to pinpoint a particular source and manage it due to the variability of the pollutants in space, time, and the socio-economic factors involved.This study aims to answer two questions: the possibility to use mobile measurement systems to identify the major sources that contribute to higher aerosol concentration in time and space and if low-cost particulate matter sensors are suitable for land-use-based modeling using conventional regression analysis and machine learning methods such as random forest and neural networks.The data used was collected using the OPC-N2 sensor from Alphasense Ltd., as a part of the measurement campaign of the project Urban Climate under Change, Phase 1 and 2 [2016-2023].