Mustafa Kamal

Mr. Mustafa Kamal

GIS and Remote Sensing Analyst
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 November 2020 in Remote Sensing Applications: Society and Environment
Verified
Journal Article
Open access
RYRuoyu Yang
Ruoyu Yang
ZAZia U. Ahmed
Zia U. Ahmed
USUrs Schulthess
Urs Schulthess
Mustafa KamalMustafa Kamal
Mustafa Kamal
RRRahul Rai
Rahul Rai
Improving agricultural productivity of smallholder farms (which are typically less than 2 ha) is key to food security for millions of people in developing nations. Knowledge of the size and location of crop fields forms the basis for crop statistics, yield forecasting, resource allocation, economic planning, and for monitoring the effectiveness of development interventions and investments. We evaluated three different full convolutional neural network (F–CNN) models (U-Net, SegNet, and DenseNet) with deep neural architecture to detect functional field boundaries from the very high resolution (VHR) WorldView-3 satellite imagery from Southern Bangladesh. The precision of the three F–CNN was up to 0.8, and among the three F–CNN models, the highest precision, recalls, and F-1 score was obtained using a DenseNet model. This architecture provided the highest area under the receiver operating characteristic (ROC) curve (AUC) when tested with independent images. We also found that 4-channel images (blue, green, red, and near-infrared) provided small gains in performance when compared to 3-channel images (blue, green, and red). Our results indicate the potential of using CNN based computer vision techniques to detect field boundaries of small, irregularly shaped agricultural fields.

10 November 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Mustafa KamalMustafa Kamal
Mustafa Kamal
USUrs Schulthess
Urs Schulthess
TKTimothy Krupnik
Timothy Krupnik
Mung bean (Vigna radiata) plays an important role providing protein in the rice-based diet of the people in Bangladesh. In the coastal division of Barisal, our study area, the average farm size is less than 0.5 ha and individual fields measure about 0.10 ha. The availability of free Sentinel-2 optical satellite data acquired at a 10 m ground sampling distance (GSD) may offer an opportunity to generate crop area estimates in smallholder farming settings in South Asia. We combined different sources of in situ data, such as aerial photographs taken from a low flying manned aircraft, data collected on the ground, and data derived from satellite images to create a data set for a segment based classification of mung bean. User’s accuracy for mung bean was 0.98 and producer’s accuracy was 0.99. Hence, the accuracy metrics indicate that the random tree classifier was able to identify mung bean based on 10 m GSD data, despite the small size of individual fields. We estimated the mung bean area for 2019 at 109,416 ha, which is about 40% lower than the Department of Agricultural Extension estimates (183,480 ha), but more than four times higher than the 2019 data reported by the Bangladesh Bureau of Statistics (26,612 ha). Further analysis revealed that crop production tends to be clustered in the landscape by crop type. After merging adjacent segments by crop type, the following average cluster sizes resulted: 1.62 ha for mung bean, 0.74 ha for rice (Oryza sativa), 0.68 ha for weedy fallow and 0.40 ha for a category of other crops. This explains why 10 m GSD satellite data can be used for the identification of predominant crops grown in specific regions of South Asia.

29 September 2025 in International Journal of Remote Sensing
Verified
Journal Article
Open access
TDTatenda Dzurume
Tatenda Dzurume
Roshanak DarvishzadehRoshanak Darvishzadeh
Roshanak Darvishzadeh
TDTimothy Dube
Timothy Dube
TAT.S Amjath-Babu
T.S Amjath-Babu
MBMutasim Billah
Mutasim Billah
Andy NelsonAndy Nelson
Andy Nelson

10 July 2025 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Verified
Journal Article
Open access
PDF file
BBBikesh Bade
Bikesh Bade
USUrs Schulthess
Urs Schulthess
GBGerald Blasch
Gerald Blasch
SSSonam Rinchen Sherpa
Sonam Rinchen Sherpa
HSHim Lal Shrestha
Him Lal Shrestha
SNSujan Nepali
Sujan Nepali
Precise mapping and tracking of wheat crops are crucial to improve agricultural management, particularly for small farms in challenging landscapes such as Nepal. By utilizing temporal Sentinel-2 imagery, this research maps wheat fields by examining phenological stages using machine learning methods, which enhances classification accuracy. Sentinel-2, a component of the Copernicus program by the European Space Agency, offers high-quality multispectral images for precise monitoring of crop growth over time. Two classification models, Random Forest (RF) and Support Vector Machine (SVM), were employed to distinguish wheat from non-wheat areas. The accuracy of classification was improved by integrating in-situ data collected with Kobo Toolbox. The findings showed that Random Forest performed better than SVM, reaching 99% accuracy in training and 86% in validation, with 56%of the study region classified as wheat. RF's outstanding performance is due to its capacity to manage temporal and spectral intricacies, particularly in capturing the phenological cycle of crops. This research showcases how machine learning, specifically Random Forest, can enhance the accuracy of wheat mapping for small farms by analyzing phenological stages effectively, with plans to apply these methods to rice and maize in the future.

5 October 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
TAT.S Amjath-Babu
T.S Amjath-Babu
SASyed Nurul Alam
Syed Nurul Alam
DCDipok Kumar Choudhury
Dipok Kumar Choudhury
MBMutasim Billah
Mutasim Billah
SASreejith Aravindakshan
Sreejith Aravindakshan
TKTimothy Krupnik
Timothy Krupnik
Fall Armyworm (FAW), Spodoptera frugiperda, is recognized as a major threat to maize production in Africa, the Americas (its native range in North, Central, and South America), and increasingly in Asia following its recent spread across the continent. This study presents a comprehensive assessment of FAW pest dynamics and yield impacts in Bangladesh, focusing on the efficacy of agroecological, cultural and chemical pest management practices. Multi-year data (2019–2022) on FAW population dynamics were collected through nationwide monitoring, farmer surveys, and satellite-based landscape diversity assessments across 31 out of 64 districts. Using structural equation modeling (SEM), we analyzed relationships among FAW damage at different maize growth stages to yield, given agronomic practices, and environmental variables. Our results suggest that FAW damage in Bangladesh ranged from 7.8 to 9.8% yield loss, which was significantly lower than 11.6% reported in Zimbabwe, 17–24% in India, 32% in Ethiopia and 47% in Kenya. Yield losses associated with indicators of vegetative and cob damage ranged from 0.78 t ha-1 in 2020 to 0.98 t ha-1 in 2022, but overall productivity remained above 9 t ha-1. Integrated pest management practices embedding agroecological principles, that harness ecological processes and reduce reliance on external inputs—such as minimum tillage, intercropping, diversified cropping systems, mechanical and manual weed control, and larval handpicking, consistently reduced crop damage. Monitoring data were strongly correlated with field-level symptoms, reinforcing the value of pheromone traps in guiding integrated pest management (IPM) decisions. Results highlight the effectiveness of non-chemical strategies and suggest that blanket pesticide applications without field scouting may be unnecessary under current FAW pressure. These findings support evidence-based IPM policies and encourage resource-efficient pest management in Bangladesh.