Nisar Ali

Nisar Ali

Auto-generated profile, based on publicly available information

Nisar Ali

Faculty of Engineering and Applied Science, University of Regina, Regina, SK, Canada

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
11 June 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
NANisar Ali
Nisar Ali
AMAhmed Mohammed
Ahmed Mohammed
Abdul BaisAbdul Bais
Abdul Bais
SBSamia Berraies
Samia Berraies
YRYuefeng Ruan
Yuefeng Ruan
JSJatinder S. Sangha
Jatinder S. Sangha
This study explored how to use UAV-based multi-spectral imaging, a plot detection model, and machine learning (ML) algorithms to predict wheat grain yield at the field scale. Multispectral data was collected over several weeks using the MicaSense RedEdge-P camera. Ground truth data on vegetation indices was collected utilizing portable phenotyping instruments, and agronomic data was collected manually. The YOLOv8 detection model was utilized for field scale wheat plot detection. Four ML algorithms–decision tree (DT), random forest (RF), gradient boosting (GB), and extreme gradient boosting (XGBoost) were used to evaluate wheat grain yield prediction using normalized difference vegetation index (NDVI), normalized difference red edge index (NDRE), and green NDVI (G-NDVI) data. The results demonstrated the RF algorithm's predicting ability across all growth stages, with a root mean square error (RMSE) of 43 grams per plot (g/p) and a coefficient of determination ( $R^{2}$ ) value of 0.90 for NDVI data. For NDRE data, DT outperformed other models, with an RMSE of 43 g/p and an $R^{2}$ of 0.88. GB exhibited the highest predictive accuracy for G-NDVI data, with an RMSE of 42 g/p and an $R^{2}$ value of 0.89. The study integrated isogenic bread wheat sister lines and checked cultivars differing in grain yield, grain protein, and other agronomic traits to facilitate the identification of high-yield performers. The results show the potential use of UAV-based multispectral imaging combined with a detection model and machine learning in various precision agriculture applications, including wheat breeding, agronomy research, and broader agricultural practices.

11 December 2023
Verified
Conference Paper
Closed access
HAHassan Ashfaq
Hassan Ashfaq
UAUsama Arshad
Usama Arshad
RARaja Hashim Ali
Raja Hashim Ali
ZAZain Ul Abideen
Zain Ul Abideen
MSMuhammad Huzaifa Shah
Muhammad Huzaifa Shah
Abu Bakar SiddiqueAbu Bakar Siddique
Abu Bakar Siddique
Fostering crop health is vital for global food security, underscoring the need for effective disease detection. This research introduces an innovative artificial intelligence (AI) model designed to enhance the detection and diagnosis of diseases in tomato plants, particularly focusing on Early Blight and Late Blight. Significantly, our model leverages cutting-edge image processing techniques to improve disease detection efficiency, outperforming traditional methods in terms of speed and accuracy. Our results demonstrate an impressive model accuracy of 92.58% on training data and 86.83% on validation data, showing the effectiveness of AI in diagnosing plant diseases. These high accuracy rates underline the potential of our model for timely disease classification, allowing for immediate and appropriate interventions. However, our research also identified a potential overfitting problem in the model’s performance. To address this, we propose using regularization and data augmentation techniques to enhance the model’s generalizability on unseen data. Additionally, we delve into inherent challenges that plague AI-based plant disease detection, such as the scarcity of diverse datasets and the difficulty of achieving broad generalizability across different plant species. In identifying potential solutions for these issues, our research lays the groundwork for the wider and more practical implementation of AI technologies in agriculture.

7 March 2025 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
NANisar Ali
Nisar Ali
MUMuhib Ullah
Muhib Ullah
AMAhmed Mohammed
Ahmed Mohammed
Abdul BaisAbdul Bais
Abdul Bais
SBSamia Berraies
Samia Berraies
JSJatinder S. Sangha
Jatinder S. Sangha
Fusarium head blight (FHB) is a significant disease affecting wheat, one of the most vital global crops, with severe implications for crop yield and food safety. Traditional FHB detection methods have limitations, highlighting the need for innovative and sustainable solutions. This review investigates the Fusarium species responsible for FHB, the disease’s life cycle, symptoms, and FHB mycotoxins affecting human and animal health. We focus on deep learning (DL) techniques for FHB detection that improve accuracy, resource efficiency, environmental sustainability, and error reduction compared to conventional methods. DL models, integrated with RGB and spectral imaging and enhanced by transfer learning and data augmentation, achieve high precision in detecting FHB across wheat varieties. Advancements in UAV-based RGB and spectral imaging paired with DL show promising results for early detection, reducing crop damage and lowering carbon emissions. However, data imbalance, background noise, and model overestimation persist. Optimization strategies and multi-modal approaches integrating imaging with environmental data have been proposed to enhance model robustness. This review underscores DL’s potential to improve FHB detection, crop yield, and sustainable agricultural practices. Future directions emphasize IoT integration, real-time low-power electronics, and blockchain for data security, addressing ethical concerns in labour and data privacy in agriculture.

18 September 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
AMAhmed Mohammed
Ahmed Mohammed
NANisar Ali
Nisar Ali
Abdul BaisAbdul Bais
Abdul Bais
YRYuefeng Ruan
Yuefeng Ruan
RCRichard D. Cuthbert
Richard D. Cuthbert
JSJatinder S. Sangha
Jatinder S. Sangha
Wheat breeding enhances wheat crops for better environmental resistance and higher yield potential. Experimental breeding lines are evaluated based on their yield potential, where quantifying spikes per unit area and kernels per spike is crucial for assessment. This study introduces SPINEL (SPIke and kerNEL), a framework that combines unmanned aerial vehicle (UAV)-captured multispectral imaging and field-captured RGB camera imaging for spike and kernel quantification. This approach utilizes YOLOv8 models, each tailored for a specific detection task. The first model detects plots in UAV-captured multispectral images with a mean average precision (mAP) score of 95%, while the second model, trained to detect spikes in the same dataset, demonstrates an mAP score of 86%. The third model detects spikes and kernels in field-captured RGB images with an 85% mAP score. The first two models aid in estimating the spike density in each field plot. The third model provides the estimated number of kernels in spikes of each unique breeding line. Spikes per field plot and kernels per spike serve as key quantification metrics. The SPINEL framework utilizes the geolocation information of the multispectral images and associates these metrics with breeding lines at the field level. This integration provides a clear visual representation of spike count and average kernels per spike for each field plot. SPINEL offers a precise, automated solution for phenotyping in wheat breeding, promising significant advancements in crop improvement strategies.

12 November 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
NANisar Ali
Nisar Ali
MUMuhib Ullah
Muhib Ullah
Abdul BaisAbdul Bais
Abdul Bais
SBSamia Berraies
Samia Berraies
YRYuefeng Ruan
Yuefeng Ruan
JSJatinder S. Sangha
Jatinder S. Sangha
Fusarium head blight (FHB) poses a critical threat to global wheat production, compromising yield and quality through mycotoxin contamination. Traditional methods, such as laboratory assays and visual inspections, are labour-intensive, costly, and impractical for large-scale monitoring. Although remote sensing based on unmanned aerial vehicles (UAVs) offers a promising alternative, existing approaches using axis-aligned bounding boxes (AABBs) struggle with arbitrary orientations, large aspect ratios, and dense wheat spike arrangements, limiting detection accuracy. To address these challenges, we introduce a UAV-based remote sensing framework for detecting oriented FHB-infected wheat spikes under real field conditions. We propose a novel modified hybrid YOLO architecture for detecting oriented bounding boxes (OBBs) that integrates the efficiency of YOLOv10 with YOLOv11’s orientation-aware detection capabilities. To enhance lesion visibility in UAV images, we utilize pixel-level cubic power stretching, which amplifies the contrast of FHB-infected regions while normalizing overexposed backgrounds. Experimental results demonstrate state-of-the-art performance; for example, our Hybrid-YOLO-x achieves 93.8% mAP@0.5, surpassing YOLOv8x and YOLOv11x by 3.1% and 1.3%, respectively. It reduces parameters by 30.4% (vs. YOLOv8x) and 17.7% (vs. YOLOv11x) while lowering GFLOPs by 28.3% (vs. YOLOv8x) and 7.1% (vs. YOLOv11x). The model also achieves 67.7% mAP @ 0.5–0.95, outperforming YOLOv8x by 4.3% and YOLOv11x by 0.6%. Our hybrid model also outperforms other state-of-the-art OBB detectors, such as S2ANet, ROI-Transformer, R2CNN, utilizing 12.8% fewer parameters and 5.4% lower computational cost.