Does ShrimpKrishi mobile application facilitate smart shrimp farming? A field study

Introduction

Shrimp farming, growing of delicate shrimp post larvae to a table size in controlled pond conditions is a proven aquabusiness model practiced in different scales-extensive to intensive-with varying technology adoption and investments. The shrimp production in India was 0.845 MMT and it alone contributed 68% of the country's seafood export earnings with a value of 5 billion USD in 2023-24 (MPEDA, 2024). However, shrimp farming has been less profitable in recent years mainly due to volatile farm gate price, emerging diseases and climate related risks (Kumaran et al. 2021) [10] . Smart farming approach based on informed decision making using real-time data on pond parameters, incorporating precision farming principles for reduction in cost of production, disease prevention through adoption of better practices, and adoption of prudent crop planning intune with the market requirements is a viable strategy for profitable farming. Though the farmers document all the farming operations in their farm records, a smart digital application which can provide synthesized information based on real-time pond parameters is an innovative tool that aids in efficient farming. Ahamed et al. reported that smart farming approach with digital tools offer real-time insights into individual shrimp and overall farm conditions, facilitating proactive management and timely interventions. FAO (2024) [5] emphasized that the performance of aquaculture systems is functional to the adoption of technologies that promote precision farming, support decision-making and farm management. A mobile phonebased shrimp farm management application-CIBA ShrimpKrishi was designed and launched to aid the shrimp farmers in their farm management. The application is downloaded from the Google play store free of cost. Through this application the shrimp farmers can digitally store their farm data regarding farming operations on realtime basis, access technical solutions based on the data given from the inbuilt expert systems, store, retrieve and share data for advanced recommendations. Previous research has specified that the mobile phone based smart applications could bridge information gaps, increase crop yields, empower farmer decision-making, and enhance the overall farm productivity (Singh et [25,8,22] (Ndzi et al., 2014; Aker and Ksoll, 2016; Sontakki and Subash, 2017; Karanasios and Slavova, 2018) [16,2,27,7] . Smart mobile applications that provide solutions to specific needs and challenges of farmers with intuitive interfaces and direct navigation tend to have higher adoption rates (Peleg-Adler, 2018; [19,17,18,12,24] . Similarly, favourable experiences and peer group word-of-mouth endorsements contribute to the trust (Ishida, et al. 2016) [6] . However, apprehensions about data privacy, the safety of personal cum farm-related information, cyber security threats and data breaches can lead to hesitancy in using digital apps (Kenny and Regan, 2021; Demestichas, 2020) [9,4] . In this backdrop, an www.extensionjournal.com investigation was taken up to know its level of adoption by the farmers, their perception about its usefulness on realtime pond management and improving the efficiency of shrimp farming so that the application can be updated in tune with the end-user feedback.

Methods

Development of CIBA ShrimpKrishi smart mobile

phone application ShrimpKrishi app, an android-based mobile application, was developed following the Software Development Life Cycle (SLDC) approach (Fig1) by developing a framework for data acquisition, design, coding and validation of decision support modules, and its implementation as depicted in Fig2. The contents of the modules were coded into programming language wherein the programme specifications were transformed into software commands. The application was developed using the data bases created through Structured Query Language (MySQL) as back end and the latest version of Android Studio Ladybug with Java language as front end, the procedure followed by earlier studies in the farming sector (Kumaran et al. 2022) [11] . The internal reliability and validity of the app modules were assessed using pertinent consistency tests and content validation by the subject matter specialists.

Efficiency evaluation of the mobile application

The present investigation used a mixed approach to evaluate the efficiency of the developed mobile application, viz., (i) end user awareness in terms of cumulative user downloads, (ii) comparative analysis of farming attributes 'before and after' its adoption and (iii) perceived utility of the modules. Previously, Kumaran et al. (2022) [11] evaluated a mobile application on shrimp farming in terms of its awareness among the end users, knowledge acquisition in terms of knowledge gain, perceived utility of the mobile app modules, subject matter queries received and responded through the mobile application and desk-top review of the mobile application. Whereas, Pliakoura et al. (2018) [20] adopted a combination of both with and without user participation in the evaluation of an agricultural mobile application. The perceived efficiency of the app was assessed based on its relative influence on twelve farming attributes as indicators. These attributes were identified through focus group discussions with a group of subject matter researchers as indicators to measure the efficacy of a farm management tool. The attributes selected include: farm productivity, cost of production, shrimp size at harvest, cropping duration in days, production risks, real-time data decision making, record keeping and traceability, resource use efficiency, farm income and profitability, capacity development, market-led farming and overall farming efficiency. The perceived efficiency was measured based on a three-point measurement procedure as given in the Table-1. In addition, the perceived usefulness of the app was measured as the perception of end users on identified functional attributes in terms of its utility in farm decision making, design functionality and extension service function. A Likert scale type perception index containing 16 statements reflecting the above stated attributes was designed in consultation with the domain resource experts, extension education experts and innovative farmers and validated its content. The enduser perceptions were recorded in a three-point continuum, viz., 'greater extent', 'to some extent' and 'least extent' with the scores of three (3), two (2) and one (1) respectively. The scores of all the responses were added to arrive at the perception score of the individual respondent. The mobile application has a cumulative download of 2853 in the year 2025 of which 84% was from India. Among the above population a sample of 180 end-user shrimp farmers who were found using it continuously were purposively selected from the states of Andhra Pradesh and Tamil Nadu as respondents to ascertain the perceived efficiency of the mobile application. A structured questionnaire was developed and used to collect the primary data directly contacting the identified farmer end-users. The anonymity of the respondent and ethical considerations pertaining to the data were taken into account by including a declaration in the questionnaire which stated that the information provided by a respondent is required for research purpose and will not be disclosed with any other person or entity. The null hypothesis postulated for the study was that the mobile application did not significantly contribute for smart shrimp farming after its adoption. Descriptive statistics like percentage analysis, mean and standard deviation were done using statistical software SPSS version 17.0 to clean and consolidate the data. The Shapiro-Wilk test was done to evaluate the normality of the primary data which indicated that the sample data did not follow the normal distribution. Therefore, non-parametric Wilcoxon signed rank test was employed to compare the farming attributes 'before and after' use of mobile application for efficient farming. Wilcoxon Signed-Rank test is the non-parametric analysis commonly applied when the assumption of normality is not satisfied (Tan Kesgin, 2025; Q, Xing et al. 2022) [28,21] . The average values of previous crops data on the selected attributes were collected from the farm records of the respondents and used as pre-app use data.

Results and Discussion a. Development and modules of CIBA ShrimpKrishi mobile application

CIBA ShrimpKrishi app was developed in four vernacular languages viz., English, Hindi, Tamil and Telugu and available as cost-free download from the Google play store. It is a dynamic mobile application that works totally as per the data recorded by the end-user. The end user has to log-in by providing basic data about his/her personal profile, farm profile and farm-infrastructure inventory to complete the registration. Once registered, the dash board of the app appears and shows four modules viz., Pond wise one-time entry, Pond wise daily entry, recommendations and post a query (Fig3). Based on the farm profile data already entered, the app displays pond wise data capturing forms for further data entry. The user can record pond wise data on the listed parameters whenever an operation or activity is done in that pond. The recording of farming data is of three kinds: 1. Pond wise entry-once in a crop: Parameters like pond preparation practices, seed selection and stocking www.extensionjournal.com details (stocking density, seed size), harvesting and production are done only once during the crop, hence need to be recorded and saved only once. 2. Pond wise entry-whenever the data available: Data on water quality parameters, input applications etc. are done periodically (eg. weekly once) and such data need to be recorded and saved whenever they are practiced. 3. Pond wise entry-mandatory daily entry: Data on water quality parameters like DO, pH, ammonia, feed rationing and application, animal health monitoring and the cost associated with the inputs applied/practices are to be recorded and saved every time as per their applications.

The end user has to enter operational data pond wise from the first day of culture (DoC-1) compulsorily. The most important aspect is that whenever any data is entered in any of the forms clicking the SAVE button in each page is mandatory, then only the data are saved and added with the existing data on that parameter. As the data are accumulated on each pond parameter as per the crop duration, the app started displaying the status of pond parameters as graphs on shrimp survival%, FCR and biomass, water quality parameters and the cost incurred on various aspects for every pond by a finger stroke in the dash board itself. This is the unique feature of this mobile app (Fig4). Additionally, three expert systems respectively on shrimp feed management, water quality management and shrimp disease management are integrated in to the mobile application under the daily entry module. When the data entered by the end-user on the water quality, feed management and health management deviate from the optimum parameters the recommendations module displays alert messages to the end-user along with technical advisories to be followed to correct the deviations (Fig5). The application can store the complete data of a crop cycle pond wise in it and end-user farmer can re-check the data on any day of culture by choosing the DoC calendar in the data entry menu. The other unique feature of the app is that the end user can download the data pond wise during any DoC in the form of an excel sheet or PDF document and can share it with anyone for their decision making (Fig6). Similarly, the data can be downloaded and saved after the crop for further reference and decision making. Through this option the application extended the scope for accessing the real-time data from remotely located shrimp farms to remotely observe, provide customized technical advisories and plan for a harvesting decision in tune with market demand. ShrimpKrishiApp in Windows platform: Based on the field feedback rendered by the end-users regarding difficulty in entering the data in the mobile phones, the app was converted to work in windows platform subsequently (Fig6). Presently, the end-users can enter and view the data using their lap-top for ease of entry. Both the Android and Windows platforms are synchronized so that the data entered and saved in one mode can be seen in the other mode. Whatever be the platform 'saving of each data entered' is crucial for displaying the correct results.

Assessing the efficiency of mobile application 1. Awareness among the primary stakeholders

Adequate efforts were taken to create awareness among the end users about the modules of the app and its usefulness through presentations in farmers' conclaves, seminars, display of app profiles in exhibitions and other stakeholder conventions. As a result of it as on date the app has a cumulative download of 3039 (Fig7). However, which needs to be enhanced by creating awareness among the potential users. The play console showed that app was mostly used in India (85.60%) followed by Indonesia (1.50%), Ecuador (1.33%), Bangladesh (1.25%) and Philippines (0.87%). Anand and Kumaran (2017) reported that shrimp farmers regularly seek technical advisories even from online sources and are receptive towards accessing technology information through mobile applications. During the field investigation several key informant farmers reported that though the farmers were aware of the app and its usefulness, its rate of adoption for farm management was inadequate due to their apprehension that through this app their farming data including the economics were remotely monitored which they felt may threaten the privacy of their farming operations. This may be because the app is hosted at the host institution's server. Earlier studies on mobile app use efficiency also reported that concerns about data privacy, farm-related information, cyber security threats and data breaches can lead to reluctance in using certain apps (Kenny and Regan, 2021; Demestichas, 2020) [9,4] . Therefore, sharing of information on farming operations to get advisories needs to be kept as optional. Further, the application may be delinked from the host institution and hosted in an open cloud server so that it is adopted extensively.

Efficiency of the mobile application on farming parameters

The Wilcoxon signed rank analysis indicated that adoption of ShrimpKrishi application for managing the shrimp farms has significantly enhanced the overall efficiency of the farming (p ≤ 0.01) (Table -2) and contributed for smart shrimp farming. All the 12 farming attributes taken for assessment have shown significant improvement after the app was used for real-time data-based farm management. Farms that adopted this app significantly improved pond productivity (up to 0.5t/ha), harvested larger shrimp size (up to 3 g), improved the real-time decision making, record keeping and traceability, resource use efficiency, farming income, market led farming and capacity development. Similarly, adoption of the app facilitated in reduction of cropping duration, production risks and production cost significantly. These results are in line with the earlier findings which stated that mobile applications have facilitated in precision farming with enhanced farming efficiency, premium market, improved financial control, bridge information gaps, greater resilience to climate-related challenges and providing access to knowledge and services (Saikanth et al. 2023; Singh et al. 2023; Kareska, 2023; FAO, 2024) [22,25,8,5] . The respondent farmers reported that www.extensionjournal.com in recent times shrimp farmers were asked to submit their farming records to meet the traceability requirements of the farm produced shrimps to meet the food safety requirements of shrimp importing countries. Similarly, many insurance companies have launched their insurance products for supporting shrimp farming in India and they needed such farm monitoring applications to monitor their client farms. Considering these developments, the ShrimpKrishi application need to be customized to meet the traceability requirements of shrimp farmers and facilitate the insurance companies who started providing insurance support to shrimp farmers to monitor their client farms.

End users perception on the efficiency of mobile application

It may be seen from the Table-3 that majority of the mobile app end-user respondents felt that the ShrimpKrishi app facilitated in precision farming through efficient pond management (87%), selection of quality shrimp seed (80%), disease prevention and management (77%), optimizing water quality parameters (75%), contributing for cost reduction (73%), improving the productivity and income (70%), supplement the extension workers function of advisory service (68%), providing pond specific solutions based on the real-time data (67%) and in pond management and decision making (65%). Further, the end-users opined that the app modules are interconnected and aided in digital record keeping (65%), the design and navigation are user friendly (65%), availability of the app in vernacular language helped in easy operation (63%), aided in data sharing and getting quality farm advisories (61%), working of app in windows platform aids in easy data entry and use (60%) and it paved for accessing updated scientific information from a reliable source (58%). Bidit opined that Bangladesh farmers faced difficulty in using mobile phone advisories which are not given in their vernacular language. Digital extension tools on shrimp farming revealed positive findings on their efficiency, content and functionality (Alagappan and Kumaran, 2016; Kumaran et al. 2022) [3,11] . Therefore, the results on the efficiency of the mobile application on farming parameters, perception of the endusers on its functional usefulness and the awareness among the stakeholders indicated that the CIBA ShrimpKrishi mobile application aided the farmers in achieving maximum potential output with given inputs and technology i.e. technical efficiency and contributed for the smart farming. Above all, the results and field experiences indicated that the app needs to be periodically updated and hosted in an open-source platform for its extensive adoption among the shrimp farmers not only in India but at the global level too. Cropping duration In days 5.

Production risks High-3; Same-2; Low-1 6.

Real-time data based decision making Efficient-3; to some extent -2; Low-1 7.

Record keeping and traceability Efficient-3; to some extent -2; Low-1 8.

Resource use efficiency Efficient-3; to some extent -2; Low-1 9.

Farm income & profitability High-3; Same-2; Low-1 10.

Capacity development Efficient-3; to some extent -2; Low-1 11.

Market-led farming High-3; Same-2; Low-1 12.

Overall farming efficiency Efficient-3; to some extent -2; Low-1 App aids in precision farming through efficient pond management 86.67 ± 6.66 2.

App helps in selection of quality shrimp seed 80.00 ± 8.83 3.

App aids in disease diagnostics to prevent and manage diseases 76.67 ± 6.66 4.

App aids in optimizing water quality parameters and their management 75.00 ± 5.00 5.

App aids in efficient pond management and reducing the production cost 73.33 ± 1.67 6.

App aids in improving the productivity and income 71.67 ± 3.33 7.

App facilitates in supply chain integration (inputs and market) 70.00 ± 3.33 8.

App can supplement the extension workers function of advisory service 68.33 ± 3.34 9.

App provides pond specific solutions based on the real-time data 68.33 ± 1.66 10.

App aids in real-time data based pond management and decision making 66.67 ± 3.32 11.

App modules are interconnected and aids in digital record keeping 65.00 ± 1.67 12.

App's design and functionality and navigation are user friendly 65.00 ± 3.34 13.

App is in vernacular language and helps in easy operation. 63.33 ± 6.66 14.

The app aids in data sharing and getting quality farm advisories 61.66 ± 5.01 15.

The working of app in windows platform aids in easy data entry and use. 60.00 ± 3.33 16.

App paved the way to access scientific information from the researchers. 58.33 ± 1.67 *Multiple responses Efforts need to be made to customize this application to www.extensionjournal.com meet the traceability requirements of shrimp buyers and facilitate the insurance companies who started providing insurance support to shrimp farmers to monitor their client farms. Further, adequate efforts are needed to create awareness among the stakeholders and motivate them in adopting this useful tool for shrimp farm management at a wider scale. Additionally, it is important that the application needs to be updated periodically in line with the technology advancements and end-user requirements to sustain its usability.

References

1. Ahmed F, Bijoy MHI, Hemal HR, Noori SRH. Smart aquaculture analytics: Enhancing shrimp farming in Bangladesh through real-time IoT monitoring and predictive machine learning analysis. Heliyon. 2024;10:e37330.
2. Aker JC, Ksoll C. Can mobile phones improve agricultural outcomes? Evidence from a randomized experiment in Niger. Food Policy. 2016;60:44-51.
3. Alagappan M, Kumaran M. Perception of aquaculture extension personnel on information technology enabled expert system for shrimp aquaculture. Journal of Inland Fisheries Society of India. 2016;48(2):38-47.
4. Demestichas K, Peppes N, Alexakis T. Survey on security threats in agricultural IoT and smart farming. Sensors. 2020;20(22):6458.
5. FAO. The State of World Fisheries and Aquaculture 2024 -Blue Transformation in action. Rome: FAO; 2024. p. 264.
6. Ishida K, Slevitch L, Siamionava K. The effects of traditional and electronic word-of-mouth on destination image: A case of vacation tourists visiting Branson, Missouri. Administrative Sciences. 2016;6(4):12.
7. Karanasios S, Slavova M. Understanding the impacts of mobile technology on small holder agriculture. In: Digital technologies for agricultural and rural development in the global south. 2018. p. 111.
8. Kareska K. Digital agriculture as a response to the challenges in the modern agricultural sector. SSRN. 2023;4549236.
9. Kenny U, Regan A. Co-designing a smartphone app for and with farmers: Empathising with end-users' values and needs. Journal of Rural Studies. 2021;82:148-160.
10. Kumaran M, Anand PR, Ashok Kumar J, Muralidhar M, Kumaraguru Vasagam KP, Vijayan KK. Assessment of perceived farming risks, communication of risk management practices, and evaluation of their efficiency in Pacific white shrimp (Penaeus vannamei) farming: A survey-based cross-sectional study. Aquaculture International. 2021;29:2713-2730.
11. Kumaran M, Anand PR, Ashok Kumar J, Muralidhar M, Ambasankar K, Panigrahi A, et al. Development of a mobile application for Pacific white shrimp (Penaeus vannamei) farming and evaluation of its efficiency in technology communication and feedback. Aquaculture International. 2022.
12. Lee I, Shin YJ. Machine learning for enterprises: Applications, algorithm selection, and challenges. Business Horizons. 2020;63(2):157-170.
13. Marine Products Export Development Authority. Aquaculture production and area under culture state wise data of India. 2024.
14. Milovanović S. The role and potential of information technology in agricultural improvement. Economics of www.extensionjournal.com Agriculture. 2014:471-485.
15. Abdillahi Alawy MKK, Allen C, Subharwal M, Jadhav A, Parr M. Effectiveness of mobile agri-advisory service extension model: Evidence from DirecT2Farm program in India. World Development Perspectives. 2019;13:25-33.
16. Ndzi DL, Harun A, Ramli FM, Kamarudin ML, Zakaria A, Shakaff AYM, et al. Wireless sensor network coverage measurement and planning in mixed crop farming. Computers and Electronics in Agriculture. 2014;105:83-94.
17. Ni L, Liu W, Huang Y, Pan M. Technology adoption and promotion in the age of skepticism: Examining COVID-19 mitigation through technological and human factors. Journal of Promotion Management. 2023;1-22.
18. Øksnebjerg L, Woods B, Waldemar G. Designing the ReACT app to support self-management of people with dementia: An iterative user-involving process. Gerontology. 2019;65(6):673-685.
19. Peleg-Adler R, Lanir J, Korman M. The effects of aging on the use of handheld augmented reality in a route planning task. Computers in Human Behavior. 2018;81:52-62.
20. Pliakoura A, Beligiannis G, Kontogeorgos A. Mobile device applications usability assessment: The example of an agricultural management application. Journal of Agricultural Informatics. 2018;9(3):55-64.
21. Xing Q, Tu H, Yang M, Chen G, Tang Q, Yi S, et al. Evaluation of cold tolerance and gene expression patterns associated with low-temperature stress in giant freshwater prawn, Macrobrachium rosenbergii. Aquaculture Reports. 2022;24:101172.
22. Saikanth DRK, Mary KJ, Nagar AK, Yadav R, Abhijeet, Thilagam P, et al. Mobile applications for agricultural transformation: Types, impacts, case studies, and recommendations. International Journal of Statistics and Applied Mathematics. 2023;8(6):405-414.
23. Bhargavi KSS, Kumaran M, Ravisankar T, Muralidhar M, Sathishkumar T, Ananthan PS, et al. Risk perception and assessment in Pacific white shrimp farming: An exploratory study. International Journal of Agricultural Extension and Social Development. 2024;7(7):203-210.
24. Sennuga SO, Ujoyi SA, Bamidele J, Onjewu SS, LaiSolarin WI. Exploring the role of smartphone apps for livestock farmers data management extension and informed decision making in Nigeria. International Journal of Probiotics and Dietetics. 2023;3(2):46-53.
25. Singh NK, Sunitha NH, Tripathi G, Saikanth DRK, Sharma A, Jose AE. Impact of digital technologies in agricultural extension. Asian Journal of Agricultural Extension, Economics and Sociology. 2023;41(9):963970.
26. Sivakami S, Karthikeyan C. Evaluating the effectiveness of expert system for performing agricultural extension services in India. Expert Systems with Applications. 2009;36:9634-9636.
27. Sontakki BS, Subash SP. Farmer innovation system: Rethinking the way we look at farmer innovations. In: Agriculture under climate change: Threats, strategies and policies. 2017. p. 383-391.
28. Kesgin TR. Revisiting trend stability using MannKendall and Wilcoxon signed-rank tests through innovative method comparisons. Sustainability. 2025;17:10454.
29. Wilcoxon F. Individual comparisons by ranking methods. Biometrics Bulletin. 1945;1:80-83.