Sudheer Bhakare

Mr. Sudheer Bhakare

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
7 September 2024 in Atmosphere
Verified
Journal Article
Open access
PDF file
SBSudheer Bhakare
Sudheer Bhakare
SGSara Gesso
Sara Gesso
Marco VenturiniMarco Venturini
Marco Venturini
DZDino Zardi
Dino Zardi
Laura TrentiniLaura Trentini
Laura Trentini
MPMarcello Petitta
Marcello Petitta
We compare three machine learning models—artificial neural network (ANN), random forest (RF), and convolutional neural network (CNN)—for spatial downscaling of temperature at 2 m above ground (T2M) from a 9 km ERA5-Land reanalysis to 1 km in a complex terrain area, including the Non Valley and the Adige Valley in the Italian Alps. The results suggest that CNN performs better than the other methods across all seasons. RF performs similar to CNN, particularly in spring and summer, but its performance is reduced in winter and autumn. The best performance was observed in summer for CNN (R2 = 0.94, RMSE = 1 °C, MAE = 0.78 °C) and the lowest in winter for ANN (R2 = 0.79, RMSE = 1.6 °C, MAE = 1.3 °C). Elevation is an important predictor for ANN and RF, whereas it does not play a significant role for CNN. Additionally, CNN outperforms others even without elevation as an additional feature. Furthermore, MAE increases with higher elevation for ANN across all seasons. Conversely, MAE decreases with increased elevation for RF and CNN, particularly for summer, and remains mostly stable for other seasons.

1 January 2025 in Atmosphere
Verified
Journal Article
Open access
PDF file
SBSudheer Bhakare
Sudheer Bhakare
MMMichael Matiu
Michael Matiu
ACAlice Crespi
Alice Crespi
DZDino Zardi
Dino Zardi
This study examines the performance of three machine learning models—namely, Artificial Neural Network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN)—for spatial downscaling of seasonal forecasts of daily minimum temperature from 12 km to 250 m horizontal resolution. Downscaling is carried out with a one-month lead time, with analysis split into short-term (1 to 8 days) and extended (9 to 28 days) forecast periods, allowing a detailed assessment of the performance of models over time. Results suggest that CNN outperforms ANN and RF, achieving lower Root Mean Square Error (ranging from 2.04 °C to 2.66 °C) and Mean Absolute Error (1.59 °C to 2.03 °C) along with higher correlation (0.75 to 0.88) and reduced bias (−0.38 °C to −0.68) across all seasons, for the short term. The CNN model also exhibits superior performance in frost prediction, with the highest F1 score (0.78) and lowest False Discovery Rate (0.30) in predicting frost events, particularly in early spring for the short-term forecast period over 2010–2018. However, errors increase in transitional months, like April, and in the extended forecast period, confirming the intrinsic challenges inherent to predicting frost events in these months. Despite the decreased skills for extended forecast periods, results suggest that the CNN model’s effectiveness for spatial downscaling of minimum temperature and frost forecasting over complex terrain provides a valuable tool for frost risk management.

28 July 2025 in Journal of Hydrology: Regional Studies
Verified
Journal Article
Open access
SBSudheer Bhakare
Sudheer Bhakare
MMMichael Matiu
Michael Matiu
DZDino Zardi
Dino Zardi

15 May 2023
Verified
Conference Paper
Open access
SBSudheer Bhakare
Sudheer Bhakare
SGSara Dal Gesso
Sara Dal Gesso
MVMarco Venturini
Marco Venturini
DZDino Zardi
Dino Zardi
The output of Global climate models has a coarse resolution, which is unsuitable for practical applications like agricultural services. Downscaling is the approach used to create fine-resolution data from coarse one. There are two main approaches to downscale climate model outputs: Dynamical Downscaling (DD) and Statistical downscaling (SD). In DD, higher-resolution climate models called regional climate models (RCM) are used. RCM use lower resolution climate models as boundary conditions and physical principles to reproduce local weather. These RCMs use physical equations and computational calculations to estimate local climate, making them computationally intensive and time-consuming. On the other hand, for SD, a statistical relationship is developed between the historically observed climate data and the climate model output for the same historical period. The relationship is used to develop future climate data. In recent years Machine learning-based statistical downscaling approaches have gained popularity due to their learning abilities from large datasets.We have developed a artificial neural network-based machine learning algorithm to downscale coarser resolution temperature to a finer one over Trentino–South Tyrol (north-eastern Italian Alps). In addition to that, considering the high correlation of elevation with temperature, elevation data of high resolution (1km x 1km) from the digital terrain model is used to train the model. We have developed different neural network models with additional complexity in terms number of layers in the model and compared them with a benchmark standard linear model and nonlinear model such as support vector regression for their performance.

20 January 2025
Verified
Conference Paper
Open access
SBSudheer Bhakare
Sudheer Bhakare
SGSara Dal Gesso
Sara Dal Gesso
MVMarco Venturini
Marco Venturini
DZDino Zardi
Dino Zardi
The precise representation of spatial temperature is important for practical applications like agriculture where they require local information at very high resolution for managing agricultural activities. In recent times, statistical downscaling methods, specifically those utilizing machine learning methods are gaining importance due to their computational of time efficiency over dynamic downscaling.This study focuses on enhancing the downscaling of spatial temperature over complex terrain using machine learning algorithms, particularly Random Forest (RF), Artificial Neural Networks (ANN), and Convolutional Neural Networks (CNN). The primary aim of this study is to identify the most promising machine learning model for downscaling gridded temperature at 2 meters from 9 km to 1 km over Non and Adige valleys. Additionally, we aim to apply these models for potential frost identification for the months of March, April, and May. We used static predictors such as Shutter Radar Topography Mission (SRTM) elevation which plays an important role in complex terrains to improve the performance of models. In addition to that, dynamic predictors such as zonal and meridional winds (U, V), windspeed, surface pressure (SP), etc. are used as auxiliary inputs. The study’s methodology includes training and evaluating the performance of three machine learning models using statistical metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), R square (R2), and Mean Bias Error (MBE). Furthermore, we used other metrics such as recall, precision, and F1 score for assessing model performance for frost identification.Our results show CNN models outperform other models across all the seasons with the best performance in summer (RMSE=1, MAE= 0.78, R2=0.94) and the least in winter (RMSE=1.3, MAE=1, R2=0.87). All These models exhibit a consistent pattern of having good performance in summer and least in winter. The superiority of the CNN model can be attributed to its ability to capture spatial patterns in temperature data which makes it more reliable for complex terrains. Additionally, for frost identification, CNN models show better performance with the highest F1 score across March, April, and May.