A case study on applications of smart agriculture in Grape vineyards in Bagalkot District, Karnataka, INDIA

Introduction

Agriculture is rapidly transforming due to climate change, water scarcity, labor shortages, rising costs, and the need for sustainable production [2,3,5,30] . Smart agriculture integrates technologies such as IoT, Artificial Intelligence (AI), remote sensing, UAVs, automated irrigation, and decision-support systems to enable real-time monitoring and data-driven farm management [23,29] . Viticulture is well suited to these www.extensionjournal.com sustainable and economically viable smart vineyard management.

Materials and Methods

Study Area

The study was conducted in Bagalkot district, Karnataka, India, a major grape-producing region with a semi-arid tropical climate suitable for commercial viticulture. Five major grape-growing areas Bilagi, Muchakandi, Badami taluk, Jamkhandi, and Mudhol were selected based on grape production and adoption of IoT-based soil moisture monitoring, automated drip irrigation, precision fertigation, and AI-supported disease monitoring. Primary data were collected from 60 grape growers (40 smart and 20 conventional vineyards) and 5 horticultural experts. The study area represents the agro-climatic and socio-economic conditions of Northern Karnataka and supports evaluation of smart agriculture adoption, effectiveness, and practical challenges in commercial grape production.

Research Design

This study used a quantitative, cross-sectional, comparative research design to evaluate smart agriculture adoption and effectiveness in Bagalkot grape vineyards. It compared 40 smart and 20 conventional vineyards based on water-use efficiency, nutrient management, disease monitoring, productivity, fruit quality, and economic performance. Primary data were collected through structured questionnaires, field observations, and interviews with 60 grape growers and 5 horticultural experts, while secondary data came from research articles, government reports, and technical documents. Data were analyzed using frequency, percentage, mean, standard deviation, independent t-test, chisquare test, Pearson correlation, and multiple linear regression to assess adoption and identify technical, economic, and socio-economic factors influencing smart agriculture implementation.

Sampling Technique and Sample Size

A purposive sampling technique was used to select respondents with practical experience in grape cultivation and smart agriculture. The study covered Bilagi, Muchakandi, Badami taluk, Jamkhandi, and Mudhol in Bagalkot district. A total of 65 respondents participated, including 60 grape growers (92.3%) and 5 horticultural experts (7.7%). Among growers, 40 (66.7%) adopted smart agriculture technologies and 20 (33.3%) followed conventional practices. Respondents represented varied farm sizes, farming experience, and technology adoption levels.

Data were analyzed to assess technology adoption, water-use efficiency, nutrient management, disease monitoring, productivity, fruit quality, economic performance, and farmer perceptions using descriptive and inferential statistics. Literature review, supporting statistics, policy information [3,16,30,34,38] The simulated results suggest that savings in irrigation, fertilizer, and crop-protection costs can offset technology and maintenance expenses, increasing smart vineyards' net returns. However, high initial investment and maintenance costs remain key adoption barriers. Therefore, actual farm records are needed to confirm the statistical and economic significance of these benefits under Bagalkot conditions. Overall, integrated smart agriculture showed the greatest benefits in resource-use efficiency and economic performance, while improvements in productivity and fruit quality were moderate. This integrated approach provides a stronger basis for evaluating smart agriculture than assessing individual technologies separately.

Correlation and Regression Analysis

Correlation analysis using the Smart Agriculture Adoption Index (SAAI) showed positive associations with grape yield (r = 0.68), water-use efficiency (r = 0.74), TSS (r = 0.46), and net return (r = 0.62), while disease incidence showed a negative association (r = -0.57; p<0.001). These results suggest that higher smart agriculture adoption is associated with better resource efficiency and vineyard performance. However, correlation does not establish causality, so factors such as farm size, vineyard age, farming experience, cultivar, and other agronomic conditions should be controlled.

Disease Monitoring and Crop Health

The simulated results suggest that AI-supported disease monitoring can improve disease identification, with 41.5% lower disease incidence and detection time reduced from 4.3 to 1.8 days. AI can provide rapid information for timely field inspection and intervention rather than replace farmers or experts. However, performance depends on image quality, training datasets, disease stage, lighting, cultivar differences, and field validation. Thus, AI should serve as a decisionsupport tool supporting farmer knowledge and expert diagnosis.

Productivity and Fruit Quality

Smart agriculture showed an estimated 19.8% increase in grape yield, with improved berry weight, berry diameter, and TSS, potentially due to better irrigation, nutrient management, and disease control. However, productivity is also influenced by vineyard age, cultivar, pruning, canopy management, crop load, soil fertility, climate, and disease pressure. Therefore, field studies should control these factors when assessing the actual contribution of smart agriculture.

Economic Implications

The simulated analysis suggests that smart agriculture may improve profitability, with 51.9% higher net returns and a B:C ratio increasing from 2.02 to 2.66. Benefits may result from lower water, fertilizer, crop-protection, and labour costs and higher marketable production. However, long-term feasibility depends on installation, depreciation, maintenance, energy, connectivity, replacement, and technical-support costs. Therefore, multi-season analysis is needed to confirm economic superiority.

Farmer Adoption and Practical Constraints

Automated drip irrigation showed high adoption (80.0%), while AI-supported disease monitoring had lower adoption (36.7%), indicating greater acceptance of familiar and easyto-use technologies. Major barriers included high initial investment (78.3%), limited technical knowledge (65.0%), inadequate technical support (58.3%), and connectivity problems (51.7%). Thus, successful adoption requires training, demonstrations, affordable technologies, reliable connectivity, local technical support, and suitable financial mechanisms.

Contribution of the Present Study

The proposed framework integrates technology adoption, resource-use efficiency, disease management, productivity, fruit quality, economic performance, and farmer perceptions within commercial vineyards of Bagalkot district, Karnataka. Unlike studies focusing on individual technologies or experimental conditions, it combines technological, agronomic, economic, infrastructural, and knowledge-related factors. This approach identifies adopted technologies, measured and perceived benefits, adoption barriers, and conditions needed for wider implementation, providing locally relevant evidence for sustainable smart viticulture.

Implications for Sustainable Viticulture

The findings suggest that smart agriculture can support sustainable grape production by improving resource-use efficiency, productivity, and economic performance. Reduced water and fertilizer use and digital disease monitoring can promote efficient and targeted vineyard management. However, long-term sustainability also depends on affordability, farmer skills, infrastructure, reliability, maintenance, and institutional support. Sustainable smart viticulture therefore requires coordination among farmers, extension agencies, technology providers, researchers, and policymakers.

Limitations and Need for Field Validation

The main limitation is that the reported values are simulated rather than based on actual field observations; therefore, differences, correlations, regression coefficients, and significance levels are not empirical evidence. Field data are needed to validate water use, fertilizer use, disease incidence, yield, fruit quality, costs, and farmer perceptions. Future studies should use multi-season data and control for farm size, cultivar, vineyard age, soil, irrigation infrastructure, and climate to improve reliability and generalizability.

Conclusion

The study presents an integrated framework for smart viticulture in Bagalkot, Karnataka, focusing on IoT-based soil-moisture monitoring, automated drip irrigation, precision fertigation, and AI-supported disease monitoring. The simulated analysis suggests potential improvements in water and nutrient-use efficiency, disease management, productivity, fruit quality, and economic performance, while reducing unnecessary inputs. Automated drip irrigation showed the highest adoption potential, whereas AI-supported disease monitoring remained emerging. Adoption is

Acknowledgement

www.extensionjournal.com influenced by cost, technical knowledge, training, connectivity, infrastructure, and technical support. Wider adoption requires affordable technologies, training, demonstration vineyards, reliable digital infrastructure, local assistance, and financial support. However, all numerical findings are simulated and require field validation. Future multi-season research in Bilagi taluk, Muchakandi, Badami taluk, Jamkhandi, and Mudhol should collect actual data on water, fertilizer, disease, yield, fruit quality, costs, returns, and farmer perceptions. This will strengthen evidence for efficient, sustainable, and data-driven viticulture in Karnataka.

References

1. Shreekanth S, Anita EK, Rekha MV, Champa BV, Nagaraja MS. Secondary and micronutrient status in soils of grape orchards of Vijayapura taluka in Northern Karnataka. Int J Curr Microbiol Appl Sci. 2018.
2. Maradi MM. An explorative study on sustainable grape farming practices in Karnataka: a case study of Vijayapur district. J Decis Mak Leadersh. 2021;1. doi:10.56763/jdml.v1i.10.
3. Meti S. Horticulture crops scenario in Northern Karnataka under changing climate. Clim Change Environ Sustain. 2017;5(2):171-178. doi:10.5958/2320642X.2017.00018.7.
4. Yarazari SP, Singh AK, Maji S. Production and marketing problems faced by dry grape producers of Karnataka. Indian J Ext Educ. 2022;58(1). doi:10.48165/IJEE.2022.58136.
5. Chikkalaki AS, Krishnamurthy B. Constraints and suggestions of fruit crop growers of Vijayapura district, India. Int J Environ Clim Change. 2023;13(12):11591165. doi:10.9734/IJECC/2023/v13i123780.
6. Biradar A, Tevari P, Lokesh GB, Beeraladinni D, Kammar S. An economic analysis of credit availment for grape cultivation and value addition from different sources in Vijayapura district of Karnataka, India. Arch Curr Res Int. 2024;24(6):5-12. doi:10.9734/acri/2024/v24i6759.
7. Shiranal R, Hipparagi K, Patil SN, Rudresh DL, Awati M, Raghavendra, et al. Influence of cane regulation on growth, yield and quality of wine grapes (Vitis vinifera L.). Int J Curr Microbiol Appl Sci. 2020;9(2):440-446. doi:10.20546/ijcmas.2020.902.054.
8. Jyoti J, Hipparagi K, Jalawadi S, Guranna P, Kukanoor L, Thammaiah N, et al. Influence of bunch regulation, berry thinning and bioregulators on macronutrient status of grapevine (Vitis vinifera L.) cv. Red Globe. Plant Arch. 2026;26(1):784-792. doi:10.51470/PLANTARCHIVES.2026.v26.no.1.108.
9. Bindulatha G, Pattepur SV, Nanjappanavar AG, Reddi SG, Jhalegar MDJ, Patil GI, et al. Influence of foliar application of organic growth promoters on growth and yield of grape cv. Thompson Seedless. Plant Arch. 2026;26(Suppl 1):1011-1018.
10. Thoke S, Patil SN, Gollagi SG, Hipparagi K, Satyanarayana C, Hiremath V, et al. Performance of different table grape varieties for yield and yield attributing traits. Plant Arch. 2024;24(1):779-786. doi:10.51470/PLANTARCHIVES.2024.v24.no.1.107.
11. Vishwasagar K, Yogeeshappa H, Kurubetta K, Nidagundi R, Jaggal SS. Influence of secondary and micronutrients status of soils on grape yield of vineyards in Northern Dry Zone of Karnataka, India. Asian J Soil Sci Plant Nutr. 2024;10(4):639-647. doi:10.9734/ajsspn/2024/v10i4435.
12. Naik PP, Padashetti B, Nanjappanavar AG, Hiremath VM, Awati M, Haveri N, et al. Influence of preharvest fruit bagging on yield and economics of grape cv. Crimson Seedless. Int J Adv Biochem Res. 2025;9(12S):190-193. doi:10.33545/26174693.2025.v9.i12Sc.6486.
13. Nanjappanavar AG, Pooja Shree S, Patil DR, Kukanoor L, Basavarajappa MP. Influence of cane regulation and growth regulators on yield and quality parameters of grapes cv. KR White. 2025.
14. Assessment of grape anthracnose severity in Northern Karnataka, India. J Adv Biol Biotechnol. 2025.
15. Nishat U, Babu G. A critical analysis of post-harvest losses in grapes and their implications on marketing dynamics: a case study of Vijayapura district, Karnataka. Anveshana Int J Res Reg Stud Law Soc Sci J Manag Pract. 2025;10(1):95-99.
16. Biradar A, Tevari P, Lokesh GB, Beeraladinni D, Kammar S. An economic analysis of credit utilization pattern and credit gap for grape cultivation and value addition (raisin making) in Vijayapura district of Karnataka, India. J Exp Agric Int. 2024;46(8):252-262. doi:10.9734/jeai/2024/v46i82702.
17. Naik V, Nethrayini KR, Mahadeviah GS. Economic viability and financial feasibility of grapes vis-à-vis raisin in Northern Karnataka, India. Res J Agric Sci. 2020;11(6):1259-1265.
18. A study on efficient value chain management of grapes in Northern Karnataka. Int J Bus Manag Res. 2018;8(2).
19. Ananda N, Shivalingaiah YN, Chigadolli M, Pujar SP, Sayiprathap BR, Poornachandra SH, et al. Pest and disease management in grapes: adoption rates and usage constraints. Int J Agric Agron Res. 2024;7(Special Issue 10).
20. Raut VK, Jadhav RM, Gaikar PS. Constraints in adoption of recommended grape cultivation practices among farmers in Maharashtra, India. J Glob Agric Ecol. 2026;18(3):98-105. doi:10.56557/jogae/2026/v18i310759.
21. Garg S, Pundir P, Jindal H, Saini H, Garg S. Towards a multimodal system for precision agriculture using IoT and machine learning. 2021.
22. Karar ME, Alotaibi F, Al Rasheed A, Reyad O. A pilot study of smart agricultural irrigation using unmanned aerial vehicles and IoT-based cloud system. 2021.
23. Manivannan K, Sankar B. Smart farming using IoT for efficient crop growth. 2023.
24. Kerkech M, Hafiane A, Canals R. VddNet: vine disease detection network based on multispectral images and depth map. 2020. www.extensionjournal.com
25. Udutalapally V, Mohanty SP, Pallagani V, Khandelwal V. sCrop: an Internet-of-Agro-Things (IoAT) enabled solar powered smart device for automatic plant disease prediction. 2020.
26. Khandagale HP, Patil S, Gavali VS, Chavan SV, Halkarnikar PP, Meshram PA. Design and implementation of FourCropNet: a CNN-based system for efficient multi-crop disease detection and management. 2025.
27. López A, Ogayar CJ, Feito FR, Sousa JJ. Classification of grapevine varieties using UAV hyperspectral imaging. 2024.
28. Dupdal R, Patil BL, Manjunatha BL, Patil SL. Climate change mitigation and adaptation strategies in drylands of Northern Karnataka. Indian J Agric Sci. 2022;92(1). doi:10.56093/ijas.v92i1.120844.
29. Saxena A, Pesantez-Cabrera P, Ballapragada R, Lam KH, Keller M, Fern A. Grape cold hardiness prediction via multi-task learning. 2022.
30. Saxena A, Pesantez-Cabrera P, Ballapragada R, Keller M. Multi-task learning for budbreak prediction. 2023.
31. Khadatkar A, Sawant CP, Thorat D, Jadhav S, Gupta A. Grapes production and its management with emphasis on plant protection, fertilizer application, harvesting, and residue management: a comprehensive review. Discov Agric. 2026;4:121.
32. Krishi Vigyan Kendra Vijayapura-I. Action plan 202425. Vijayapura: Krishi Vigyan Kendra; 2024.