Timur Rampalsingh Ahlawat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Timur Rampalsingh Ahlawat has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Alka Singh
Department of Floriculture and Landscape Architecture, ASPEE College of Horticulture and Forestry, Navsari Agricultural University, Navsari – 396 450, Gujarat, India
2 shared publications - Fatimah Khalid
Universiti Putra Malaysia
2 shared publications - Mahantappa Sangappa Sankanur
Navsari Agricultural University
2 shared publications - Mas Rina Mustaffa
Universiti Putra Malaysia
2 shared publications - Rana Ranjeet Singh
Kamdhenu University
2 shared publications - A. D. Chaudhary
Indian Institute of Foreign Trade
1 shared publication
Latest Publications
- 9 September 2026
- Published by Universiti Putra Malaysia in Journal of Intelligent Media Computing
- Vol. 1 (1) , 157
Leveraging Visual Data for Accurate Body Weight Prediction in Surti Goats
Routine weighing of goats requires suitable equipment and often involves animal handling or restraint, making repeated monitoring difficult under farm conditions. This study estimated Surti goat body weight by combining image-derived morphometric measurements (heart girth and body length extracted from two-dimensional images) with age and sex metadata. Mask Region-based Convolutional Neural Network (Mask R-CNN) was used to separate each goat from the image background before the relevant visual measurements were extracted. Dataset partitioning was conducted strictly at the Animal ID level (group-wise split) to prevent data leakage and evaluate true model generalisation on unseen animals. XGBoost, Random Forest and CatBoost were trained using the combined feature set, and their outputs were integrated through a weighted ensemble with weights of 0.5, 0.3, and 0.2 assigned to XGBoost, CatBoost, and Random Forest, respectively. On the validation set (37 goats), XGBoost achieved an 𝑅2 of 0.8514 (RMSE = 4.26 kg, MAE = 3.47 kg, MAPE = 16.27%). On the completely unseen test set (37 goats), XGBoost achieved the highest predictive performance with an 𝑅2 of 0.7955 (MSE = 29.15 kg², RMSE = 5.40 kg, MAE = 4.01 kg, and MAPE = 16.38%), while the weighted ensemble recorded an 𝑅2 of 0.7713 (MSE = 32.60 kg², RMSE = 5.71 kg, MAE = 4.13 kg, and MAPE = 16.60%). The findings show that combining visual and morphometric information under a strict group-based evaluation provides reliable, non-contact body weight estimation on unseen livestock.
- 9 September 2026
- Published by Universiti Putra Malaysia in Journal of Intelligent Media Computing
- Vol. 1 (1) , 157
Leveraging Visual Data for Accurate Body Weight Prediction in Surti Goats
Routine weighing of goats requires suitable equipment and often involves animal handling or restraint, making repeated monitoring difficult under farm conditions. This study estimated Surti goat body weight by combining image-derived morphometric measurements (heart girth and body length extracted from two-dimensional images) with age and sex metadata. Mask Region-based Convolutional Neural Network (Mask R-CNN) was used to separate each goat from the image background before the relevant visual measurements were extracted. Dataset partitioning was conducted strictly at the Animal ID level (group-wise split) to prevent data leakage and evaluate true model generalisation on unseen animals. XGBoost, Random Forest and CatBoost were trained using the combined feature set, and their outputs were integrated through a weighted ensemble with weights of 0.5, 0.3, and 0.2 assigned to XGBoost, CatBoost, and Random Forest, respectively. On the validation set (37 goats), XGBoost achieved an 𝑅2 of 0.8514 (RMSE = 4.26 kg, MAE = 3.47 kg, MAPE = 16.27%). On the completely unseen test set (37 goats), XGBoost achieved the highest predictive performance with an 𝑅2 of 0.7955 (MSE = 29.15 kg², RMSE = 5.40 kg, MAE = 4.01 kg, and MAPE = 16.38%), while the weighted ensemble recorded an 𝑅2 of 0.7713 (MSE = 32.60 kg², RMSE = 5.71 kg, MAE = 4.13 kg, and MAPE = 16.60%). The findings show that combining visual and morphometric information under a strict group-based evaluation provides reliable, non-contact body weight estimation on unseen livestock.
- 9 September 2026
- Published by Universiti Putra Malaysia in Journal of Intelligent Media Computing
- Vol. 1 (1) , 42
Comparative Evaluation of Image Classification Architectures for Surti Buffalo Muzzle Recognition With CAM-Based Explainability Analysis
Advancements in image classification architecture have greatly improved image-based animal identification. However, model comparisons are frequently restricted to classification accuracy. By comparing multiple pre-trained CNN-based and Vision Transformer architectures for muzzle image categorisation utilising predicted performance, computational efficiency, and visual interpretability, this work expands the evaluation. The accuracy, storage capacity, training time, and interpretability of pre-trained CNN and Vision Transformer architectures for muzzle image classification are evaluated in this work using four CAM variants: Grad-CAM, Grad-CAM++, Score-CAM, and XGrad-CAM. According to the results, MobileNetV2 strikes a fair balance, obtaining 96.63% accuracy with just 30.08 MB of storage and 3.80 hours of training time per fold, while DenseNet121 obtains the maximum accuracy at 97.02% with smallest variance (±0.17%). Grad-CAM++ produced the most instructive activation maps because it highlighted relevant muzzle regions more precisely than the other CAM approaches. Consistent activation maps were found to be associated with stable classification performance. However, Vision Transformer models had significant volatility in explanation quality and prediction accuracy (±2.28%). Overall, explainability is important for improving trust in these architectures because it provides insight into the reasons behind model predictions. Therefore, evaluation of image classification architectures should consider not only accuracy and efficiency but also how reliably the model's decisions can be interpreted.
- 9 September 2026
- Published by Universiti Putra Malaysia in Journal of Intelligent Media Computing
- Vol. 1 (1) , 42
Comparative Evaluation of Image Classification Architectures for Surti Buffalo Muzzle Recognition With CAM-Based Explainability Analysis
Advancements in image classification architecture have greatly improved image-based animal identification. However, model comparisons are frequently restricted to classification accuracy. By comparing multiple pre-trained CNN-based and Vision Transformer architectures for muzzle image categorisation utilising predicted performance, computational efficiency, and visual interpretability, this work expands the evaluation. The accuracy, storage capacity, training time, and interpretability of pre-trained CNN and Vision Transformer architectures for muzzle image classification are evaluated in this work using four CAM variants: Grad-CAM, Grad-CAM++, Score-CAM, and XGrad-CAM. According to the results, MobileNetV2 strikes a fair balance, obtaining 96.63% accuracy with just 30.08 MB of storage and 3.80 hours of training time per fold, while DenseNet121 obtains the maximum accuracy at 97.02% with smallest variance (±0.17%). Grad-CAM++ produced the most instructive activation maps because it highlighted relevant muzzle regions more precisely than the other CAM approaches. Consistent activation maps were found to be associated with stable classification performance. However, Vision Transformer models had significant volatility in explanation quality and prediction accuracy (±2.28%). Overall, explainability is important for improving trust in these architectures because it provides insight into the reasons behind model predictions. Therefore, evaluation of image classification architectures should consider not only accuracy and efficiency but also how reliably the model's decisions can be interpreted.
- 12 August 2026
- Published by Wiley in New Zealand Journal of Crop and Horticultural Science
- Vol. 54 (3) , e70215
Characterization of Inter‐Varietal Hybrid Progenies of Guava Using Morphological and Molecular Traits
The improvement of guava ( Psidium guajava L.) is constrained by a narrow genetic base and increasing biotic and abiotic stresses, necessitating the development and evaluation of diverse hybrid populations. This study aimed to characterize inter‐varietal F 1 hybrid progenies of guava using integrated morphological and molecular techniques to assess genetic variability and confirm hybridity. We evaluated seventy 1‐year‐old F 1 hybrids derived from crosses between four red‐pulped genotypes (Jarvi Red, Sanjari, Yogi and Exotica) and one white‐pulped genotype (VNR Bihi), along with their parental lines, under field conditions. We recorded 18 quantitative and qualitative morphological characteristics based on criteria of distinctness, homogeneity and stability (DUS). Cluster analysis was employed to examine genetic associations. Significant variability was observed among hybrids for all quantitative metrics, indicating effective recombination of paternal alleles. The application of simple sequence repeat markers for molecular characterization demonstrated moderate to high polymorphism. Fourteen polymorphic markers produced 40 alleles. The co‐dominant SSR markers were highly reproducible and strongly supported the hybridity of F 1 progenies by detecting alleles from both parental origins. The morphological and molecular analyses of these novel varietal combinations collectively indicated that the hybrid population exhibited considerable genetic diversity and identified many progenies that may be advantageous for breeding purposes. These findings highlight the effectiveness of integrating morphological descriptors with molecular markers to define guava genetic resources and identify suitable material for future breeding projects.
- 12 August 2026
- Published by Wiley in New Zealand Journal of Crop and Horticultural Science
- Vol. 54 (3) , e70215
Characterization of Inter‐Varietal Hybrid Progenies of Guava Using Morphological and Molecular Traits
The improvement of guava ( Psidium guajava L.) is constrained by a narrow genetic base and increasing biotic and abiotic stresses, necessitating the development and evaluation of diverse hybrid populations. This study aimed to characterize inter‐varietal F 1 hybrid progenies of guava using integrated morphological and molecular techniques to assess genetic variability and confirm hybridity. We evaluated seventy 1‐year‐old F 1 hybrids derived from crosses between four red‐pulped genotypes (Jarvi Red, Sanjari, Yogi and Exotica) and one white‐pulped genotype (VNR Bihi), along with their parental lines, under field conditions. We recorded 18 quantitative and qualitative morphological characteristics based on criteria of distinctness, homogeneity and stability (DUS). Cluster analysis was employed to examine genetic associations. Significant variability was observed among hybrids for all quantitative metrics, indicating effective recombination of paternal alleles. The application of simple sequence repeat markers for molecular characterization demonstrated moderate to high polymorphism. Fourteen polymorphic markers produced 40 alleles. The co‐dominant SSR markers were highly reproducible and strongly supported the hybridity of F 1 progenies by detecting alleles from both parental origins. The morphological and molecular analyses of these novel varietal combinations collectively indicated that the hybrid population exhibited considerable genetic diversity and identified many progenies that may be advantageous for breeding purposes. These findings highlight the effectiveness of integrating morphological descriptors with molecular markers to define guava genetic resources and identify suitable material for future breeding projects.
- Open Access
- 18 September 2024
- Published by IWA Publishing in Water Supply
- Vol. 24 (10) , 3423-3437
Assessment of CROPWAT 8.0 model accuracy under deficit irrigation scheduling: A sustainable path toward smart water supply
As the world confronts mounting challenges to water security, efficient irrigation becomes ever more critical. Escalating water scarcity challenges necessitate innovative smart irrigation solutions. This study investigates the potential of integrating deficit irrigation (DI) with the CROPWAT 8.0 model for sustainable and water-productive irrigation. This research evaluated the model's accuracy in generating DI schedules at 70% field capacity (FC) (T1) compared to schedules derived from frequency domain reflectometry (FDR) soil moisture sensors at 70% FC (T2). The results demonstrated economic viability and strong accuracy for T1 with consistently lower values of mean absolute error (3.6165 and 4.3987) and root mean square error (4.4447 and 5.5055) while compared to T2 across two years. In addition, T1 achieved significant water savings (43.47 and 45.16%) alongside higher water productivity (8.11 and 8.22 kg m−3), respectively, for both the years compared to full irrigation (FI). These findings highlight CROPWAT 8.0 model–driven DI scheduling as a promising smart irrigation approach for tackling water scarcity, offering economic benefits to farmers while promoting water security.
- 18 September 2024
- Published by IWA Publishing in Water Supply
- Vol. 24 (10) , 3423-3437
Open AccessAssessment of CROPWAT 8.0 model accuracy under deficit irrigation scheduling: A sustainable path toward smart water supply
As the world confronts mounting challenges to water security, efficient irrigation becomes ever more critical. Escalating water scarcity challenges necessitate innovative smart irrigation solutions. This study investigates the potential of integrating deficit irrigation (DI) with the CROPWAT 8.0 model for sustainable and water-productive irrigation. This research evaluated the model's accuracy in generating DI schedules at 70% field capacity (FC) (T1) compared to schedules derived from frequency domain reflectometry (FDR) soil moisture sensors at 70% FC (T2). The results demonstrated economic viability and strong accuracy for T1 with consistently lower values of mean absolute error (3.6165 and 4.3987) and root mean square error (4.4447 and 5.5055) while compared to T2 across two years. In addition, T1 achieved significant water savings (43.47 and 45.16%) alongside higher water productivity (8.11 and 8.22 kg m−3), respectively, for both the years compared to full irrigation (FI). These findings highlight CROPWAT 8.0 model–driven DI scheduling as a promising smart irrigation approach for tackling water scarcity, offering economic benefits to farmers while promoting water security.
- Open Access
- 2 May 2020
- Published by Sciencedomain International in Current Journal of Applied Science and Technology
- p. 1-6
Effect of De-blossoming Treatments on Physical Characteristics of Different Mango Varieties during Off-season Fruit Production under South Gujarat Conditions
An investigation was conducted during 2013-14 and 2014-15 seasons under South Gujarat conditions to study the impact of de-blossoming in six mango varieties during regular flowering season on off season fruiting characters. The investigation consisted of four de-blossoming treatments i.e. foliar sprays of Naphthalene Acetic Acid at 400 and 800 ppm, hand de-blossoming and untreated trees which were imposed on six mango varieties i.e. Amrapali, Baramasi, Neelphanso, Neelum, Ratna and Totapuri. The trial was evaluated in a Randomized Block Design with factorial concept. De-blossoming was done at full bloom stage for induction of off season flowering. Results indicated that in regular season cultivar ‘Totapuri’ recorded significantly higher fruit weight, fruit length, fruit width and fruit volume during 2013-14 and 2014-15. With regard to off-season fruiting, significantly maximum value of the above traits was observed in ‘Ratna’ cultivar. Fruit weight, volume, length and width were lowest in cv. ‘Neelphanso’ in regular as well as in off-season. Hand de-blossoming was found superior over control for fruit weight and fruit volume in all the varieties selected for this study in the coastal climate of South Gujarat.
- 2 May 2020
- Published by Sciencedomain International in Current Journal of Applied Science and Technology
- p. 1-6
Open AccessEffect of De-blossoming Treatments on Physical Characteristics of Different Mango Varieties during Off-season Fruit Production under South Gujarat Conditions
An investigation was conducted during 2013-14 and 2014-15 seasons under South Gujarat conditions to study the impact of de-blossoming in six mango varieties during regular flowering season on off season fruiting characters. The investigation consisted of four de-blossoming treatments i.e. foliar sprays of Naphthalene Acetic Acid at 400 and 800 ppm, hand de-blossoming and untreated trees which were imposed on six mango varieties i.e. Amrapali, Baramasi, Neelphanso, Neelum, Ratna and Totapuri. The trial was evaluated in a Randomized Block Design with factorial concept. De-blossoming was done at full bloom stage for induction of off season flowering. Results indicated that in regular season cultivar ‘Totapuri’ recorded significantly higher fruit weight, fruit length, fruit width and fruit volume during 2013-14 and 2014-15. With regard to off-season fruiting, significantly maximum value of the above traits was observed in ‘Ratna’ cultivar. Fruit weight, volume, length and width were lowest in cv. ‘Neelphanso’ in regular as well as in off-season. Hand de-blossoming was found superior over control for fruit weight and fruit volume in all the varieties selected for this study in the coastal climate of South Gujarat.
- 1 January 2016
- Published by Indian Academy of Horticultural Sciences in Indian Journal of Horticulture
- Vol. 73 (1) , 99-103
Standardization of dehydration technique for greenhouse cut rose var. Shakira
An investigation was conducted to evaluate optimum dehydration technique for greenhouse cut rose var. Shakira at different harvest stages, viz., bud stage, 50% open and fully opened flowers. Flowers dried at 50% open stage showed higher retention in dry weight and flower diameter though flowers dried at fully opened stage took minimum time to drying process. Among various drying techniques, microwave oven with silica gel as embedding medium took minimum time in drying and showed higher moisture loss, lower moisture content and higher dry weight, flower diameter and petal pigment retention. Further, among all treatment combinations, flowers dried at 50% open stage in microwave oven embedded with silica gel as embedding media showed best quality in terms of higher retention in dry weight, flower diameter, petal pigments (anthocyanin) along with well-maintained shape, smooth petal texture and maximum dry flower longevity.
- 1 January 2016
- Published by Indian Academy of Horticultural Sciences in Indian Journal of Horticulture
- Vol. 73 (1) , 99-103
Standardization of dehydration technique for greenhouse cut rose var. Shakira
An investigation was conducted to evaluate optimum dehydration technique for greenhouse cut rose var. Shakira at different harvest stages, viz., bud stage, 50% open and fully opened flowers. Flowers dried at 50% open stage showed higher retention in dry weight and flower diameter though flowers dried at fully opened stage took minimum time to drying process. Among various drying techniques, microwave oven with silica gel as embedding medium took minimum time in drying and showed higher moisture loss, lower moisture content and higher dry weight, flower diameter and petal pigment retention. Further, among all treatment combinations, flowers dried at 50% open stage in microwave oven embedded with silica gel as embedding media showed best quality in terms of higher retention in dry weight, flower diameter, petal pigments (anthocyanin) along with well-maintained shape, smooth petal texture and maximum dry flower longevity.
- 1 January 2016
- Published by Indian Academy of Horticultural Sciences in Indian Journal of Horticulture
- Vol. 73 (1) , 145-148
Effect of packaging and storage temperature on shelf-life of okra pods
The experiment comprised of packing okra pods in rigid plastic crates and LDPE bags of 25, 50, 75 and 100 micron thickness with subsequent storage at 12 and 16°C. Packaged okra pods in LDPE bags of 50 micron thickness and stored at 12°C emerged as the best post harvest treatment combination. Pods subjected to this treatment combination had the best visual appearance, lower chilling injury, lower physiological loss in weight and optimal marketability. This treatment combination suppressed quality deterioration and extended the shelf-life of okra by up to 12 days.
- 1 January 2016
- Published by Indian Academy of Horticultural Sciences in Indian Journal of Horticulture
- Vol. 73 (1) , 145-148
Effect of packaging and storage temperature on shelf-life of okra pods
The experiment comprised of packing okra pods in rigid plastic crates and LDPE bags of 25, 50, 75 and 100 micron thickness with subsequent storage at 12 and 16°C. Packaged okra pods in LDPE bags of 50 micron thickness and stored at 12°C emerged as the best post harvest treatment combination. Pods subjected to this treatment combination had the best visual appearance, lower chilling injury, lower physiological loss in weight and optimal marketability. This treatment combination suppressed quality deterioration and extended the shelf-life of okra by up to 12 days.
- 1 January 2015
- Published by Indian Academy of Horticultural Sciences in Indian Journal of Horticulture
- Vol. 72 (2) , 157-161
Performance of ‘Alphonso’ as a source of pollen for its hybrids ‘Sonpari’ and ‘Neelphonso’ as female parents in mango
To incorporate the desirable traits of ‘Alphonso’ into its hybrids, a new breeding programme of back crossing the developed hybrids such as ‘Sonpari’ (‘Alphonso × Baneshan’) and ‘Neelphonso’ (‘Neelam × Alphonso’) with ‘Alphonso’ as pollen donor parent was undertaken to find out the compatibility of ‘Alphonso’ with its hybrids, ‘Sonpari’ and ‘Neelphonso’. The results revealed that fruit set was 88.91% in cross ‘Sonpari’ × ‘Alphonso’ and 78.43% in cross ‘Neelphonso’ × ‘Alphonso’. Fruit retention (%) was reduced drastically from fruit set stage till 14 days after pea stage (DAPS) but attained almost steady value from 35 DAPS onwards till harvest. The fruit retention (%) at harvest was higher in the crossed fruits of ‘Sonpari’ × ‘Alphonso’ (3.13%) compared to ‘Neelphonso’ × ‘Alphonso’ (0.94%). The crossed fruits of ‘Sonpari’ × ‘Alphonso’ produced fruit length of 13.4 cm, which was at par with Sonpari (13.5 cm), however lesser fruit width (9.9 cm) than Sonpari (11.1 cm). Crossed fruits of ‘Neelphonso’ × ‘Alphonso’ with fruit length (10.8 cm) and fruit width (5.7 cm) were higher than fruit length and width of Neelphonso. Similarly, fruit weight of hybrid fruits derived from crossed ‘Sonpari’ × ‘Alphonso’ (512.4 g) was significantly less than its female parent (527.2 g) but superior over Alphonso (331.4 g). Hybrids fruits of ‘Neelphonso’ × ‘Alphonso’ (235.2 g) was significantly higher than its female parent (216 g) but less than Alphonso. Based on this experiment, pollens of ‘Alphonso’ showed good compatibility with both ‘Sonpari’ and ‘Neelphonso’, which may be utilized as pollen parent for pollination in these two newly developed hybrid varieties for their further improvement.
- 1 January 2015
- Published by Indian Academy of Horticultural Sciences in Indian Journal of Horticulture
- Vol. 72 (2) , 157-161
Performance of ‘Alphonso’ as a source of pollen for its hybrids ‘Sonpari’ and ‘Neelphonso’ as female parents in mango
To incorporate the desirable traits of ‘Alphonso’ into its hybrids, a new breeding programme of back crossing the developed hybrids such as ‘Sonpari’ (‘Alphonso × Baneshan’) and ‘Neelphonso’ (‘Neelam × Alphonso’) with ‘Alphonso’ as pollen donor parent was undertaken to find out the compatibility of ‘Alphonso’ with its hybrids, ‘Sonpari’ and ‘Neelphonso’. The results revealed that fruit set was 88.91% in cross ‘Sonpari’ × ‘Alphonso’ and 78.43% in cross ‘Neelphonso’ × ‘Alphonso’. Fruit retention (%) was reduced drastically from fruit set stage till 14 days after pea stage (DAPS) but attained almost steady value from 35 DAPS onwards till harvest. The fruit retention (%) at harvest was higher in the crossed fruits of ‘Sonpari’ × ‘Alphonso’ (3.13%) compared to ‘Neelphonso’ × ‘Alphonso’ (0.94%). The crossed fruits of ‘Sonpari’ × ‘Alphonso’ produced fruit length of 13.4 cm, which was at par with Sonpari (13.5 cm), however lesser fruit width (9.9 cm) than Sonpari (11.1 cm). Crossed fruits of ‘Neelphonso’ × ‘Alphonso’ with fruit length (10.8 cm) and fruit width (5.7 cm) were higher than fruit length and width of Neelphonso. Similarly, fruit weight of hybrid fruits derived from crossed ‘Sonpari’ × ‘Alphonso’ (512.4 g) was significantly less than its female parent (527.2 g) but superior over Alphonso (331.4 g). Hybrids fruits of ‘Neelphonso’ × ‘Alphonso’ (235.2 g) was significantly higher than its female parent (216 g) but less than Alphonso. Based on this experiment, pollens of ‘Alphonso’ showed good compatibility with both ‘Sonpari’ and ‘Neelphonso’, which may be utilized as pollen parent for pollination in these two newly developed hybrid varieties for their further improvement.
- 1 December 2009
- Published by International Society for Horticultural Science (ISHS) in Acta Horticulturae
- No. 847,p. 321-326
STORAGE OF JASMINE (JASMINUM SAMBAC) IN PASSIVE MAP
ISHS IX International Symposium on Postharvest Quality of Ornamental Plants STORAGE OF JASMINE (JASMINUM SAMBAC) IN PASSIVE MAP
- 1 December 2009
- Published by International Society for Horticultural Science (ISHS) in Acta Horticulturae
- No. 847,p. 321-326
STORAGE OF JASMINE (JASMINUM SAMBAC) IN PASSIVE MAP
ISHS IX International Symposium on Postharvest Quality of Ornamental Plants STORAGE OF JASMINE (JASMINUM SAMBAC) IN PASSIVE MAP