Rashmi Gupta

Prof. Dr. Rashmi Gupta


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
18 December 2021 in Agronomy
Verified
Journal Article
Open access
PDF file
MEMartin Engen
Martin Engen
ESErik Sandø
Erik Sandø
Benjamin SjølanderBenjamin Sjølander
Benjamin Sjølander
SASimon Arenberg
Simon Arenberg
RGRashmi Gupta
Rashmi Gupta
Morten GoodwinMorten Goodwin
Morten Goodwin
Farm-scale crop yield prediction is a natural development of sustainable agriculture, producing a rich amount of food without depleting and polluting environmental resources. Recent studies on crop yield production are limited to regional-scale predictions. The regional-scale crop yield predictions usually face challenges in capturing local yield variations based on farm management decisions and the condition of the field. For this research, we identified the need to create a large and reusable farm-scale crop yield production dataset, which could provide precise farm-scale ground-truth prediction targets. Therefore, we utilise multi-temporal data, such as Sentinel-2 satellite images, weather data, farm data, grain delivery data, and cadastre-specific data. We introduce a deep hybrid neural network model to train this multi-temporal data. This model combines the features of convolutional layers and recurrent neural networks to predict farm-scale crop yield production across Norway. The proposed model could efficiently make the target predictions with the mean absolute error of 76 kg per 1000 m2. In conclusion, the reusable farm-scale multi-temporal crop yield dataset and the proposed novel model could meet the actual requirements for the prediction targets in this paper, providing further valuable insights for the research community.

21 May 2024 in Agronomy
Verified
Journal Article
Open access
PDF file
MKMikkel Andreas Kvande
Mikkel Andreas Kvande
SJSigurd Løite Jacobsen
Sigurd Løite Jacobsen
Morten GoodwinMorten Goodwin
Morten Goodwin
RGRashmi Gupta
Rashmi Gupta
Agricultural development is one of the most essential needs worldwide. In Norway, the primary foundation of grain production is based on geological and biological features. Existing research is limited to regional-scale yield predictions using artificial intelligence (AI) models, which provide a holistic overview of crop growth. In this paper, the authors propose detecting several field-scale crop types and use this analysis to predict yield production early in the growing season. In this study, the authors utilise a multi-temporal satellite image, meteorological, geographical, and grain production data corpus. The authors extract relevant vegetation indices from satellite images. Furthermore, the authors use field-area-specific features to build a field-based crop type classification model. The proposed model, consisting of a time-distributed network and a gated recurrent unit, can efficiently classify crop types with an accuracy of 70%. In addition, the authors justified that the attention-based multiple-instance learning models could learn semi-labelled agricultural data, and thus, allow realistic early in-season predictions for farmers.


26 July 2026 in Discover Artificial Intelligence
Verified
Journal Article
Open access
PDF file
SKSusrita Khadka
Susrita Khadka
JFJoanne Teves Farstad
Joanne Teves Farstad
CSChonthichar Soythong
Chonthichar Soythong
RGRashmi Gupta
Rashmi Gupta
Promotional flyers are widely used by retailers to advertise products and prices; however, extracting structured and meaningful data from them remains a significant challenge. Their highly unstructured layouts, visual clutter, and diverse design styles make data extraction largely manual, time-consuming, and error-prone. This paper presents an automated approach for extracting products and prices from retail promotional flyers using deep learning–based computer vision techniques. The proposed pipeline integrates a YOLO-based object detection model for localising product and price regions with optical character recognition for extracting the associated text. The study focuses on visually complex Nordic retail flyers. Hundreds of flyers were curated and annotated from a SQL dataset provided by VG-LAB, capturing substantial variation in layout, typography, background noise, and image quality typical of Scandinavian retail advertising. To improve model robustness, a lightweight augmentation strategy was applied, including greyscale conversion and noise reduction. In addition, a scenario-specific fusion of YOLO-based object detection and OCR was designed and optimised for this context, enabling more reliable localisation and text extraction under challenging visual conditions. The approach was evaluated on a real-world dataset of weekly promotional flyers and showed reliable performance in detecting both product and price information. The system was also deployed through a FastAPI-based pipeline for real-time and scalable processing. This demonstrates its practical relevance for platforms such as VG-LAB’s Kupp application, where automated extraction can reduce manual effort and provide structured, searchable product information for consumers. In conclusion, the findings highlight strong potential for scalable and efficient retail flyer information extraction.