Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Aadhityaa Mohanavelu has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Monthly Streamflow Prediction by Metaheuristic Regression Approaches Considering Satellite Precipitation Data

    by Mojtaba Mehraein, Aadhityaa Mohanavelu, Sujay Raghavendra Naganna, Christoph Kulls, Ozgur Kisi

    In this study, the viability of three metaheuristic regression techniques, CatBoost (CB), random forest (RF) and extreme gradient tree boosting (XGBoost, XGB), is investigated for the prediction of monthly streamflow considering satellite precipitation data. Monthly streamflow data from three measuring stations in Turkey and satellite rainfall data derived from Tropical Rainfall Measuring Mission (TRMM) were used as inputs to the models to predict 1 month ahead streamflow. Such predictions are crucial for decision-making in water resource planning and management associated with water allocations, water market planning, restricting water supply and managing drought. The outcomes of the metaheuristic regression methods were compared with those of artificial neural networks (ANN) and nonlinear regression (NLR). The effect of the periodicity component was also investigated by importing the month number of the streamflow data as input. In the first part of the study, the streamflow at each station was predicted using CB, RF, XGB, ANN and NLR methods and considering TRMM data. In the second part, streamflow at the downstream station was predicted using data from upstream stations. In both parts, the CB and XGB methods generally provided similar accuracy and performed superior to the RF, ANN and NLR methods. It was observed that the use of TRMM rainfall data and the periodicity component considerably improved the efficiency of the metaheuristic regression methods in modeling (prediction) streamflow. The use of TRMM data as inputs improved the root mean square error (RMSE) of CB, RF and XGB by 36%, 31% and 24%, respectively, on average, while the corresponding values were 37%, 18% and 43% after introducing periodicity information into the model’s inputs.


  • Open Access

    Increased frequency of urban floodings in coastal Indian cities caused by variation in monsoon rainfall: Influencing factors, challenges, and solutions

    by Aadhityaa Mohanavelu, Bankaru-Swamy Soundharajan

    Coastal cities in India houses nearly 100 million people and are evenly distributed across India’s 7516-kilometer coastline. These cities are important centers of socio-economic activities in the country and are some of the densely populated regions in the world. A number of studies recently have predicted that there is a risk of substantial portions of these cities’ areas being lost to the sea due to sea-level rise in the next few decades, since a major portion of these cities are at a near zero elevation from the mean sea level (M.S.L). Further, in the past few decades, major coastal cities in India have been repeatedly affected by recurrent extreme rainfall events and subsequent floodings. Several studies document that rapid change in the Indian monsoon, increased frequency in the formation of cyclones and the swift changes in the hydro-climatic regime in the Indian Ocean are the major contributors to the occurrence of these extreme precipitations events. While we can safely conclude that these events are likely to occur more frequently in the future, it is important to understand the factors that control and influence these events, comprehend how the cities are and will be affected, and develop feasible policy changes and mitigation action for effective governance. In this paper, we have taken the case of Chennai – an important coastal city located in the southern part of India that has been severely affected by extreme precipitation and subsequent flooding (notably the infamous 2015 Chennai floods) in the past few years, to study the influencing factors contributing to these events and the ground challenges faced by the government machinery in planning and managing these disasters effectively. Our findings indicate that there is a notable variation in the monsoon rainfall pattern in Chennai and the net annual rainfall in the city has increased significantly in the past decade (by ~15%). Further, we found that significant urban centers in the city, especially the regions that are at near zero elevation (± 5 meters above M.S.L) are more vulnerable to flooding, and the important contributing factors to the increased severity of the recent floodings include the lack of adequate stormwater drainage infrastructure and poor policy choice of converting natural surface water bodies (lakes and ponds) into towns during the past three to four decades. We also discuss the planning and execution of Chennai city’s mitigation action during the 2021 floods, analyze its success and shortcomings, and suggest sustainable and feasible policy changes and measures that can be adopted for better management of similar events in the future in other coastal cities as well.


  • Open Access

    Modeling Multi-Objective Pareto-Optimal Reservoir Operation Policies using State-of-the-art Modeling Techniques

    by Aadhityaa Mohanavelu, Soundharajan Bankaru-Swamy, Ozgur Kisi

    A novel challenge faced by the water scientists and water managers today is the efficient management of the available water resources for meeting crucial demands such as drinking water supply and irrigation at the same time ensuring sufficient water is available for other critical activities such as hydro-power generation. Modeling of optimal operation polices is imminent for better management of reservoir systems especially under competing multiple objectives such as irrigation, flood control, water supply etc., with decreasing reliability of these systems under climate change. This study compares six different state-of-the-art modeling techniques namely; Deterministic Dynamic Programming (DDP), Stochastic Dynamic Programming (SDP), Implicit Stochastic Optimization (ISO), Fitted Q-Iteration (FQI), Sampling Stochastic Dynamic Programming (SSDP), and Model Predictive Control (MPC), in modeling pareto-optimal operational policies considering two competing reservoir operational objectives of irrigation and flood control for the Pong reservoir system in Beas River, India. Pareto-optimal (approximate) set of operation policies were derived using the six methods mentioned above based on different convex combinations of the two objectives and finally the performances of the resulting sets of pareto-optimal operational solutions were compared with respect to resilience, reliability , vulnerability and sustainability indices. Modeling results suggests that the optimal-operational solution designed via DDP attains the best performance followed by the MPC and FQI. The performance of Pong reservoir operation assessed by comparing different performance indices suggest that there is high vulnerability (~0.65) and low resilience (~0.10) in current operations and the development of pareto-optimal operation solutions using multiple state-of-the-art modeling techniques might be crucial for making better reservoir operation decisions.

  • Top Cited Papers
    Open Access

    Irrigation Induced Salinity and Sodicity Hazards on Soil and Groundwater: An Overview of Its Causes, Impacts and Mitigation Strategies

    by Aadhityaa Mohanavelu, Sujay Raghavendra Naganna, Nadhir Al-Ansari

    Salinity and sodicity have been a major environmental hazard of the past century since more than 25% of the total land and 33% of the irrigated land globally are affected by salinity and sodicity. Adverse effects of soil salinity and sodicity include inhibited crop growth, waterlogging issues, groundwater contamination, loss in soil fertility and other associated secondary impacts on dependent ecosystems. Salinity and sodicity also have an enormous impact on food security since a substantial portion of the world’s irrigated land is affected by them. While the intrinsic nature of the soil could cause soil salinity and sodicity, in developing countries, they are also primarily caused by unsustainable irrigation practices, such as using high volumes of fertilizers, irrigating with saline/sodic water and lack of adequate drainage facilities to drain surplus irrigated water. This has also caused irreversible groundwater contamination in many regions. Although several remediation techniques have been developed, comprehensive land reclamation still remains challenging and is often time and resource inefficient. Mitigating the risk of salinity and sodicity while continuing to irrigate the land, for example, by growing salt-resistant crops such as halophytes together with regular crops or creating artificial drainage appears to be the most practical solution as farmers cannot halt irrigation. The purpose of this review is to highlight the global prevalence of salinity and sodicity in irrigated areas, highlight their spatiotemporal variability and causes, document the effects of irrigation induced salinity and sodicity on physicochemical properties of soil and groundwater, and discuss practical, innovative, and feasible practices and solutions to mitigate the salinity and sodicity hazards on soil and groundwater.


  • Open Access

    Novel Ensemble Forecasting of Streamflow Using Locally Weighted Learning Algorithm

    by Rana Muhammad Adnan, Abolfazl Jaafari, Aadhityaa Mohanavelu, Ozgur Kisi, Ahmed Elbeltagi

    The development of advanced computational models for improving the accuracy of streamflow forecasting could save time and cost for sustainable water resource management. In this study, a locally weighted learning (LWL) algorithm is combined with the Additive Regression (AR), Bagging (BG), Dagging (DG), Random Subspace (RS), and Rotation Forest (RF) ensemble techniques for the streamflow forecasting in the Jhelum Catchment, Pakistan. To build the models, we grouped the initial parameters into four different scenarios (M1–M4) of input data with a five-fold cross-validation (I–V) approach. To evaluate the accuracy of the developed ensemble models, previous lagged values of streamflow were used as inputs whereas the cross-validation technique and periodicity input were used to examine prediction accuracy on the basis of root correlation coefficient (R), root mean squared error (RMSE), mean absolute error (MAE), relative absolute error (RAE), and root relative squared error (RRSE). The results showed that the incorporation of periodicity (i.e., MN) as an additional input variable considerably improved both the training performance and predictive performance of the models. A comparison between the results obtained from the input combinations III and IV revealed a significant performance improvement. The cross-validation revealed that the dataset M3 provided more accurate results compared to the other datasets. While all the ensemble models successfully outperformed the standalone LWL model, the ensemble LWL-AR model was identified as the best model. Our study demonstrated that the ensemble modeling approach is a robust and promising alternative to the single forecasting of streamflow that should be further investigated with different datasets from other regions around the world.


  • Open Access

    Trends and Non-Stationarity in Groundwater Level Changes in Rapidly Developing Indian Cities

    by Aadhityaa Mohanavelu, K. S. Kasiviswanathan, S. Mohanasundaram, Idhayachandhiran Ilampooranan, Jianxun He, Santosh M. Pingale, B.-S. Soundharajan, M. M. Diwan Mohaideen

    In most of the Indian cities, around half of the urban water requirement is fulfilled by groundwater. Recently, seasonal urban droughts have been frequently witnessed globally, which adds more stress to groundwater systems. Excessive pumping and increasing demands in several Indian cities impose a high risk of running out of groundwater storage, which could potentially affect millions of lives in the future. In this paper, groundwater level changes have been comprehensively assessed for seven densely populated and rapidly growing secondary cities across India. Several statistical analyses were performed to detect the trends and non-stationarity in the groundwater level (GWL). Also, the influence of rainfall and land use/land cover changes (LULC) on the GWL was explored. The results suggest that overall, the groundwater level was found to vary between ±10 cm/year in the majority of the wells. Further, the non-stationarity analysis revealed a high impact of rainfall and LULC due to climate variability and anthropogenic activities respectively on the GWL change dynamics. Statistical correlation analysis showed evidence supporting that climate variability could potentially be a major component affecting the rainfall and groundwater recharge relationship. Additionally, from the LULC analysis, a decrease in the green cover area (R = 0.93) was found to have a higher correlation with decreasing groundwater level than that of urban area growth across seven rapidly developing cities.


  • Open Access

    A Global Scale Estimate of Novel Coronavirus (COVID-19) Cases Using Extreme Value Distributions

    by M. Aadhityaa, K. S. Kasiviswanathan, Idhayachandhiran Ilampooranan, B. Soundharajan, M. Balamurugan, Jianxun He

    The COVID-19 pandemic has created a global crisis and the governments are fighting rigorously to control the spread by imposing intervention measures and increasing the medical facilities. In order to tackle the crisis effectively we need to know the trajectories of number of the people infected (i.e. confirmed cases). Such information is crucial to government agencies for developing effective preparedness plans and strategies. We used a statistical modeling approach – extreme value distributions (EVDs) for projecting the future confirmed cases on a global scale. Using the 69 days data (from January 22, 2020 to March 30, 2020), the EVDs model predicted the number of confirmed cases from March 31, 2020 to April 9, 2020 (validation period) with an absolute percentage error < 15 % and then projected the number of confirmed cases until the end of June 2020. Also, we have quantified the uncertainty in the future projections due to the delay in reporting of the confirmed cases on a global scale. Based on the projections, we found that total confirmed cases would reach around 11.4 million globally by the end of June 2020.The USA may have 2.9 million number of confirmed cases followed by Spain-1.52 million and Italy-1.28 million.