Rahul Ghosh

Mr. Rahul Ghosh

Computer Science, University of Minnesota, Minneapolis, Minnesota, USA

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
30 April 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
CLChenxi Lin
Chenxi Lin
ZJZhenong Jin
Zhenong Jin
David J. MullaDavid J. Mulla
David J. Mulla
RGRahul Ghosh
Rahul Ghosh
KGKaiyu Guan
Kaiyu Guan
YCYaping Cai
Yaping Cai
Timely and accurate monitoring of tree crop extent and productivities are necessary for informing policy-making and investments. However, except for a very few tree species (e.g., oil palms) with obvious canopy and extensive planting, most small-crown tree crops are understudied in the remote sensing domain. To conduct large-scale small-crown tree mapping, several key questions remain to be answered, such as the choice of satellite imagery with different spatial and temporal resolution and model generalizability. In this study, we use olive trees in Morocco as an example to explore the two abovementioned questions in mapping small-crown orchard trees using 0.5 m DigitalGlobe (DG) and 3 m Planet imagery and deep learning (DL) techniques. Results show that compared to DG imagery whose mean overall accuracy (OA) can reach 0.94 and 0.92 in two climatic regions, Planet imagery has limited capacity to detect olive orchards even with multi-temporal information. The temporal information of Planet only helps when enough spatial features can be captured, e.g., when olives are with large crown sizes (e.g., >3 m) and small tree spacings (e.g., <3 m). Regarding model generalizability, experiments with DG imagery show a decrease in F1 score up to 5% and OA to 4% when transferring models to new regions with distribution shift in the feature space. Findings from this study can serve as a practical reference for many other similar mapping tasks (e.g., nuts and citrus) around the world.

8 March 2023 in Knowledge and Information Systems
Verified
Journal Article
Closed access
PDF file
YXYiqun Xie
Yiqun Xie
WCWeiye Chen
Weiye Chen
EHErhu He
Erhu He
Xiaowei JiaXiaowei Jia
Xiaowei Jia
HBHan Bao
Han Bao
PRPraveen Ravirathinam
Praveen Ravirathinam

6 March 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
EHErhu He
Erhu He
YXYiqun Xie
Yiqun Xie
WCWeiye Chen
Weiye Chen
Sergii SkakunSergii Skakun
Sergii Skakun
HBHan Bao
Han Bao
Xiaowei JiaXiaowei Jia
Xiaowei Jia
Fairness related to locations (i.e., “where”) is critical for the use of machine learning in a variety of societal domains involving spatial datasets (e.g., agriculture, disaster response, urban planning). Spatial biases incurred by learning, if left unattended, may cause or exacerbate unfair distribution of resources, social division, spatial disparity, etc. The goal of this work is to develop statistically-robust formulations and model-agnostic learning strategies to understand and promote spatial fairness. The problem is challenging as locations are often from continuous spaces with no well-defined categories (e.g., gender), and statistical conclusions from spatial data are fragile to changes in spatial partitionings and scales. Existing studies in fairness-driven learning have generated valuable insights related to non-spatial factors including race, gender, education level, etc., but research to mitigate location-related biases still remains in its infancy, leaving the main challenges unaddressed. To bridge the gap, we first propose a robust space-as-distribution (SPAD) representation of spatial fairness to reduce statistical sensitivity related to partitionings and scales in continuous space. Furthermore, we propose a new SPAD-based stochastic strategy to efficiently optimize over an extensive distribution of fairness criteria, and a bi-level training framework to enforce fairness via adaptive adjustment of priorities among locations. Finally, we extend this framework with a similarity-based training strategy to improve the computational efficiency. Experiments conducted on two real-world problems, crop monitoring in the US and palm oil plantation mapping in Indonesia, show that SPAD can effectively reduce sensitivity in fairness evaluation and the stochastic bi-level training framework can greatly improve the fairness. Controlled experiments also show that similarity-based acceleration can greatly reduce the training time while keeping the prediction performance and fairness results at the same level.

21 October 2021
Verified
Conference Paper
Open access
MHMorten Hagen
Morten Hagen
PAPiyush Arora
Piyush Arora
RGRahul Ghosh
Rahul Ghosh
DTDawn Thomas
Dawn Thomas
SJSalil R Joshi
Salil R Joshi
We introduce a model for auto-complete of general queries via Bayesian inference. To that end, we address three issues: First, the problem of predicting a word given previous words in a text. Usually, the context words are treated as a directional sequence. In our approach, we introduce a set-based class language model with order-independence, modeling the context words as a set of classes. Second, towards the task of predicting the next word’s class based on the classes of previous words plus an incomplete word prefix, we present a Bayesian framework that incorporates the set-based class language model in conjunction with an ontology. Third, regarding the auto-complete problem, we provide complete query suggestions via abstract class-space search which determines similar historical queries that contain the classes of previous words plus the next word’s predicted class. Subsequently, we apply the model to auto-complete inference in a system setting, in which users can access data via natural language queries.

28 September 2021 in arXiv
Verified
Preprint
Open access
PDF file
RGRahul Ghosh
Rahul Ghosh
PRPraveen Ravirathinam
Praveen Ravirathinam
Xiaowei JiaXiaowei Jia
Xiaowei Jia
CLChenxi Lin
Chenxi Lin
ZJZhenong Jin
Zhenong Jin
Vipin KumarVipin Kumar
Vipin Kumar
The availability of massive earth observing satellite data provide huge opportunities for land use and land cover mapping. However, such mapping effort is challenging due to the existence of various land cover classes, noisy data, and the lack of proper labels. Also, each land cover class typically has its own unique temporal pattern and can be identified only during certain periods. In this article, we introduce a novel architecture that incorporates the UNet structure with Bidirectional LSTM and Attention mechanism to jointly exploit the spatial and temporal nature of satellite data and to better identify the unique temporal patterns of each land cover. We evaluate this method for mapping crops in multiple regions over the world. We compare our method with other state-of-the-art methods both quantitatively and qualitatively on two real-world datasets which involve multiple land cover classes. We also visualise the attention weights to study its effectiveness in mitigating noise and identifying discriminative time period.

15 August 2025 in arXiv
Verified
Preprint
Open access
PDF file
RYRunlong Yu
Runlong Yu
SLShiyuan Luo
Shiyuan Luo
RGRahul Ghosh
Rahul Ghosh
LLLingyao Li
Lingyao Li
YXYiqun Xie
Yiqun Xie
Xiaowei JiaXiaowei Jia
Xiaowei Jia
Retrieval-Augmented Generation (RAG) enhances language models by combining retrieval with generation. However, its current workflow remains largely text-centric, limiting its applicability in geoscience. Many geoscientific tasks are inherently evidence-hungry. Typical examples involve imputing missing observations using analog scenes, retrieving equations and parameters to calibrate models, geolocating field photos based on visual cues, or surfacing historical case studies to support policy analyses. A simple ``retrieve-then-generate'' pipeline is insufficient for these needs. We envision Geo-RAG, a next-generation paradigm that reimagines RAG as a modular retrieve $\rightarrow$ reason $\rightarrow$ generate $\rightarrow$ verify loop. Geo-RAG supports four core capabilities: (i) retrieval of multi-modal Earth data; (ii) reasoning under physical and domain constraints; (iii) generation of science-grade artifacts; and (iv) verification of generated hypotheses against numerical models, ground measurements, and expert assessments. This shift opens new opportunities for more trustworthy and transparent geoscience workflows.