Srinivasu Pappula’s research while affiliated with Tata Consultancy Services Limited and other places

... "DeepSound," a CNN-LSTM stack, extracted such patterns from calf distress calls and reached nearly 80% macro-F1 despite minimal feature engineering . A separate CNN with seven convolutional blocks classified cow "intent" calls (hunger, stress, estrus) at ~ 97 % accuracy (Patil et al., 2024), showing how spectral differences map to different motivational states of the animals. ...

Reference:

Giving Cows a Digital Voice – AI-Enabled Bioacoustics and Smart Sensing in Precision Livestock Management

... In conclusion, to predict tea quality based on antioxidant and polyphenol content, we applied state-of-the-art machine learning techniques in this study [23]. Specifically, we used ensemble models that combine Random Forest and Decision Tree algorithms. ...

Reference:

Predicting Tea Quality Based on Antioxidant and Polyphenol Content Using Ensemble Machine Learning Model

... Forests act as vital carbon sinks, and knowing the amount of biomass they contain helps scientists and policymakers make informed decisions about conservation efforts and climate change mitigation. Traditional groundbased forest inventory methods, though effective on a smaller scale, often involve labor-intensive procedures, are time-consuming, and have limited spatial coverage (Mohite et al., 2024). Such limitations make them impractical for assessing large or remote forested areas, where accessibility is often an issue (Hasmadi and Pakhriazad, 2020). ...

Reference:

A multi-source approach combining GEDI LiDAR, satellite data, and machine learning algorithms for estimating forest aboveground biomass on Google Earth Engine platform

... Literature has focused on EB, LB, and other diseases. The pie chart in FIGURE 4 illustrates the focus of research publications on potato disease predictions from 2007 to 2024 [15], [16], [17], [18], [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57], [58], [59], [60], [61], [62], [63], [64], [65], [66], [67], [68], [69], [70], [71], [72], [73], [74], [75], [76], [77], [78], [79], [80], [81], [82], [83], [84], [85], [86], [87], [88], [112] by categorizing them into four groups. The largest segment (44.4%) represents [15], [16], [17], [18], [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [86], [87], [88], [112] addressing both LB and EB and highlighting the significant impact of these diseases. ...

Reference:

Artificial Intelligence Driven Smart Farming for Accurate Detection of Potato Diseases: A Systematic Review

... Specifically for this last goal, beans are a crop that can contribute to reducing world hunger, lowering the total of 2795 million people who will suffer from hunger by the year 2050 [4]. According to [6][7][8][9], to achieve these five goals, considering the effects of climate change, the prediction of agricultural crop yield through multiple linear regressions (MLR) and essential climate variables is an efficient tool. There are 55 essential climate (a) For essential climate variables, using the National Meteorological Service (SMN)-National Water Commission (CONAGUA) database [23], daily series of precipitation and maximum-minimum temperatures were obtained. ...

Reference:

Modeling Yield of Irrigated and Rainfed Bean in Central and Southern Sinaloa State, Mexico, Based on Essential Climate Variables

... This research examines AWS's physical security, network security, data encryption, access controls, and incident response. We can learn how AWS secures its infrastructure and client data by examining these factors [9] . The research will begin by describing AWS's architecture and services. ...

Reference:

Fortifying the Cloud: Unveiling the Next- Generation Security Model of AWS

... Controlling the exchange of water and energy between plants, soil, and the atmosphere is possible through the monitoring of evapotranspiration (ET) (Ke et al., 2017). Relevant data on small-scale agricultural operations can be obtained through routine daily, monthly, and seasonal ET calculations (Anderson et al., 2012;Mohite et al., 2022). However, modern field-based procedures are time-consuming, labor-intensive, and nonreplicable. ...

Reference:

Downscaling MODIS evapotranspiration into finer resolution using machine learning approach on a small scale, Ribb watershed, Ethiopia

... Sawant et al. [11] mentioned that data science and machine learning are crucial for agricultural data analysis and decision processes in digital farm, noting that data mining, analytics, and data science have significantly benefited digital agriculture. Studies conducted on various agricultural elements have derived models and optimized resource usage and facilitated data-driven analysis for forecasts, resource optimization, and understanding of agricultural processes. ...

Reference:

Digital Agricultural Ecosystem

... Turkulainen et al., (2023) used a custom-built quadcopter UAS with a Gryphon Dynamics frame equipped with dual-RGB camera, Rikola hyperspectral camera, and MicaSense RedEdge to monitor bark beetleinduced spruce damage. Choudhury et al., (2022) utilized a DJI Mavic Mini 2 lightweight drone as the UAV to gather overhead images of a tea garden and Debnath & Saha, (2022) took images of diseased rice paddy using DJI tello drone camera. Zwieback et al., (2024) and Virnodkar et al., (2021) used satellite images of Maxar Worldview-2 and Sentinel-2, respectively as their data for DL model evaluation. ...

Reference:

Deep learning for plant stress detection: A comprehensive review of technologies, challenges, and future directions

... Considering the respective constraints of different satellite sensors, and the need to resolve dryland vegetation water status at the local plant community level, our objective was to integrate multi-sensor vegetation observations (Mohite et al., 2022) using machine-learning (ML) approaches to build (a) VOD data with enhanced spatial (500-m) and temporal (daily) resolution, and to (b) improve linkages between global satellite VOD observations and detailed plant-to-stand level water potential measurements in selected dryland systems. ...

Reference:

Enhanced Satellite Monitoring of Dryland Vegetation Water Potential Through Multi‐Source Sensor Fusion