Conference PaperPDF Available

Digital Twin Technology for Aquaponics: Towards Optimizing Food Production With Dynamic Data Driven Application Systems


Abstract and Figures

Aquaponics, or recirculating aquaculture production systems, harness the symbiotic relationship between plants and fish for food production. A large quantity of fish can be raised in a small volume of water by the effect of plants in removing toxic waste products excreted by fish; in turn the waste is broken down by microbial activity to obtain concentrated nutrients for intensive plant/crop growing. The concentration of nutrients generated is similar to hydroponic nutrient solutions. Water is conserved in the integrated process and may be reused. In this paper we consider an approach comprising self-contained aquaponics production units each of which is a closed system where the balance of fish stock and plants is monitored and controlled automatically. We provide empirical results of a simulation and a physical implementation. The design involves an online virtual production unit implemented with a simulation that is updated with data from the real system (a dynamic data driven application system). The virtual unit anticipates the performance of the real system and enabling what if analysis and optimization of the behavior of the whole system: for example to maximize production, minimize waste, conserve water and other resources, meet quality standards, and other production goals.
Content may be subject to copyright.
Digital Twin Technology for Aquaponics:
Towards Optimizing Food Production With
Dynamic Data Driven Application Systems
Ayyaz Ahmed1,2, Shahid Zulfiqar2, Adam Ghandar1?, Yang Chen1, Masatoshi
Hanai1, and Georgios Theodoropoulos1
1Southern University of Science and Technology, Shenzhen, PRC
2Al-Khawarizmi Institute of Computer Science, University of Engineering and
Technology (UET)- Lahore, Pakistan {ayyaz.ahmed,shahid.zulfiqar}
Abstract. Aquaponics, or recirculating aquaculture production systems,
harness the symbiotic relationship between plants and fish for food pro-
duction. A large quantity of fish can be raised in a small volume of water
by the effect of plants in removing toxic waste products excreted by fish;
in turn the waste is broken down by microbial activity to obtain concen-
trated nutrients for intensive plant/crop growing. The concentration of
nutrients generated is similar to hydroponic nutrient solutions. Water is
conserved in the integrated process and may be reused. In this paper we
consider an approach comprising self-contained aquaponics production
units each of which is a closed system where the balance of fish stock
and plants is monitored and controlled automatically. We provide em-
pirical results of a simulation and a physical implementation. The design
involves an online virtual production unit implemented with a simulation
that is updated with data from the real system (a dynamic data driven
application system). The virtual unit anticipates the performance of the
real system and enabling what if analysis and optimization of the behav-
ior of the whole system: for example to maximize production, minimize
waste, conserve water and other resources, meet quality standards, and
other production goals.
Keywords: Dynamic Data Driven Application System (DDDAS) ·Sim-
ulation Modelling ·Digital Twin ·Cyber-physical System ·Aquaponics.
1 Introduction
Human society faces challenges in food security and sustainability due to factors
such as urbanization, natural resource depletion and loss of biodiversity [11].
Technological innovation is significant in efforts toward food system improve-
ment that are guided for instance by intergovernmental organizations such as
?Corresponding author: Adam Ghandar, email:
2 A. Ahmed et al.
the United Nations Food and Agriculture Organization (FAO) [8] and the G203.
These efforts recognize that while in the past a focus was on boosting agriculture
production quantity (for a survey of of recent technological advances in this area
see [26]) a new focus is needed to tackle basic causes of hunger and malnutri-
tion. Efforts today focus on transformative changes across the entire value chain
in the way food is produced, consumed and distributed4[25]. For examples of
applications that involve innovation in agricultural value chains, see [27] which
proposes a hydroponic planter for urban agriculture that is designed to support
a novel service industry and value chain configuration through local production
in an urban environment; [9] looks at the linking producers of different scales,
traditional and non-traditional with customers through a network interface and
gateway so as to attain necessary attributes of volume, traceability, and consis-
tency that are important in mass production food systems but also gain benefits
of small scale production such as customized produce and local production.
According to the FAO, agricultural innovation needs to encompass diverse
stakeholders including small family farmers and local industry taking into ac-
count unique cultural and geographic constraints (technological as well as policy,
organizational and social aspects). Aquaoponics [7], can provide fish and fresh
produce that is produced, potentially, co-located with consumers in urban envi-
ronments such as rooftops thus reducing necessity for transportation and storage.
It can facilitate intensive farming for high yields in limited space with efficient
use of resources. Aquaponics has been applied to produce food in difficult and
constrained conditions, for instance the FAO describes application in the Gaza
strip [1]: an arid, urban area in protracted crisis5. The potential for aquaponics
to provide food security and sustenance in difficult constrained environments
sustainably with limited resources, and to form a component of an innovative
sustainable value chain with diverse stakeholder participation, has resulted in
recent research interest.
Aquaponics combines hydroponics (growing plants without soil) and aqua-
culture (raising fish). Fish excrete waste, these dissolved nutrients accumulate
in the water and provide plants with nutrition [24]. Water is recirculated be-
tween fish and plants resulting in a much lower requirement for water than
traditional soil based agriculture. In effect aquaponics is a holistic farming tech-
nology where a controlled ecosystem is formulated where plants and fish live in
symbiotic relation supported by microbial activity (to break down waste and
generate nutrients) [16,19].
From a whole system point of view, aquaponic implementations are complex
systems. Combining natural and human elements interacting together in com-
plex dynamics that result from factors such as heterogeneity of plants and fish,
non linear dynamics with thresholds relating to parameters (such as concentra-
tions of nutrients and water quality), feedback loops, and other factors resulting
from combining human and natural systems that are fundamentally highly chal-
Digital Twin Technology for Aquaponics 3
lenging to model accurately [14]. Due to the complexity of the aquaponic system,
it is very challenging first to to accurately model and then to predict or opti-
mize the whole system toward system goals such as to maximize production,
minimize waste, conserve water and other resources, meet quality standards,
or other performance criteria. Possibly as a result, the current state-of-the-art
cyber-physical aquaponic systems proposed in the literature do not attempt opti-
mization of the whole system [23,30]. Rather, silos or components, are controlled
by local optimization processes or decision rules based on prior assumptions. We
investigate a new approach using a dynamic data driven application system
(DDDAS) [15,6,21].
The main contributions of the paper are as follows:
Cyber-physical Aquaponic System. We describe a cyber-physical aquapon-
ics system based on Internet-of-Things (IoT) sensors for monitoring system
and environmental conditions.
Digital Twin of an Aquaponic System. A virtual aquaponic system is
implemented as a simulation and validated.
The rest of the paper is organized as follows: technological innovations in
aquaponics are reviewed in Section 2; Section 3 describes our IoT enabled phys-
ical system; Section 4 describes the virtual replica; Section 5 evaluates and val-
idates both; Section 6 concludes the paper.
2 Background and Literature Review
Digitization has been applied to obtain benefits in many spheres of society in-
cluding developing state-of-the-art production systems, see Industry 4.0 [12].
In digital twin, real time data acquisition from physical entities are connected
to simulated representations. The approach was anticipated by the concept of
Dynamic Data Driven Application Systems [4]. The uptake of digital twin tech-
nology has been slower in small enterprises although the potential benefits are
very large [28]. In other sectors apart from agriculture real time data acquisition
combined with simulation has also proven beneficial. For a selection see [22,20,5].
IoT-based Aquaponic Systems. For a recent survey of work applying au-
tomation and IoT technology for aquaponic production see [2]. Real time data
and IoT sensors enable data relating to various system parameters to be ob-
tained and analyzed. A control loop is completed when based on the data tasks
in the operation of the system are performed, for example: add fish food, alter
the water level in the fish tank, recirculate water between fish tank and grow
bed, turn on/off the grow lights, adjust the PH level, etc. Recent research re-
ports implementation of networked sensors to support monitoring key variables
such as water quality in aquaponic systems that are designed to provide locally
grown organic food in smart city concept and reduce reliance on traditional
agriculture [18].
Many recent applications have a context of providing local high quality pro-
duce in urban settings and can implement low cost integrated monitoring and
4 A. Ahmed et al.
control using micro devices such as the Arduino, Rasberry Pi and Intel Edison
to coordinate various network components and sensor feeds. For instance, in [17]
an implementation uses Rasberry Pi to monitors PH, temperature and dissolved
oxygen levels. In [23] there is a focus on the PH and its application to control
plant and fish growth rates. In [30] a mobile application to monitor temperature
and humidity and on the basis of readings control a fan, water pump and mist
maker is described. A somewhat related implementation which uses Intel Edison
as a processor is described in [29].
Analytics and Simulation Enhanced Aquaponic Systems. Various ana-
lytic techniques can be combined with real time data to provide decision support
and automated management capabilities. There is limited research in modeling
the behavior of aquaponics as a complex system. There is however work that
describes development of mathematical techniques to predict important system
variables. In [13] analytics supports a model based management strategy and
determines optimized nutrient management strategies for producing tomato and
Nile perch (Tilapia) fish by predicting and mitigating excess concentration of
total suspended solids and sodium and ammonia concentrations and balance the
concentration of nutrients for plant growth versus the water quality required for
raising fish.
3 Cyber-physical Aquaponic System
This section provides overview of the aquaponic system and implementation of
sensor hardware.
3.1 System Overview
The cyber-physical aquaponic system consists of hydroponics, aquaculture and
an IoT sensor system.
Figure 1 shows the complete schematic cycle of the aquaponics system. Water
flows from the fish tank into a mechanical filtration where solid waste is removed.
Solid waste is removed but ammonia is dissolved in water, water then enters a
bio-filter where nitrifying bacteria convert ammonia to nitrates. Ammonia is
dangerous for both fish and plants, therefore we have to convert it into nitrates
which are a fertilizer for plants. Nitrate rich water is then moved into grow bed
and plants absorb the nitrates. Cleaned water with reduced amonia and nitrates
finally returns back to the fish tank. Grow lights were installed above the grow
bed as the system is installed indoors. Multiple sensors were installed in both
the fish tank and grow bed. Air is introduced in system for the fish. It also
helps the nitrification process in bio-filter. Details of the hardware and software
components are provided in Figure 2.
3.2 Hardware Implementation
The IoT sensor system that was implemented consists of 3 main components
or modules: sensor units, networking units, and computational units, see Fig-
Digital Twin Technology for Aquaponics 5
Fig. 1: Architecture of Aquaponics System.
ure 2. The sensor data is communicated through the networking units to the
computational units for analysis in computational units.
Sensor units measure temperature, light intensity, water flow, dissolved salts
(TDS/EC sensor), and PH. The data feed is transferred through networking
components for analysis and actuation. Networking Units include an ESP8266
device for transferring data over WiFi to MQQT broker. A 4 channel mechanical
coil relay board is used to control the air and water pumps and the growth lights.
Energy saving features include switching off growth lights when ambient light is
sufficient for growth (greater than 50 lumens). MQQT Broker6is used to gather
topics sent by ESP8266, it is able to send back messages for control and actua-
tion. A secure MQQT broker is situated on the local IP on Rasberry Pi. A Rasp-
berry Pi device provides computation. It collects data from ESP8266 via broker
and we use NODE-RED to handle results and perform logging. Thingspeakis7
provides analytics functionality and visualization, it also includes functionality
for back storage. Further data storage is through MangoDB and MyPHP for
back-end processing of data. Other physical units include a water pump (15
L/min), air pump (3.5 L/min). A secondary air pump provides redundancy in
case of failure (crucial component for fish survival). We placed our system near a
window which provides natural light still we need grow lights as direct sunlight
is not available. We used two 12 watt white led panel light and one 30 watt grow
light. An automatic fish feeder for dispensing food (4 times/day) is an important
part as fish are sensitive to over eating.
6 A. Ahmed et al.
Fig. 2: Implementation of the Sensor System.
4 Simulation
The simulation code is accessible at the following url:
Monsooooon/AquaponicSim. The main simulation modules include: fish feed,
TDS, fish weight gain, PH, Nitrates and plant growth are modeled. The feed
rate depends on feed conversion ratio, fish weight and number of fish. For the
type of fish in the system we set the FCR to 0.6, this means that if fish eats
one kg of feed, it will convert 60% of it in its body weight. Figure 4 illustrates
the interaction between the system variables as modeled. The conversion rate
between them are determined by multiple environment factors, including pH,
light strength and temperatures, and will also influence the growth rate of the
plants and fish.
where Fris fish feed rate, Fcr is feed conservation ratio, wfis fish weight gain
and Nfis the number of fish in the system per meter cubic.
Digital Twin Technology for Aquaponics 7
Fig. 3: Cyber Physical Aquaponics System
Fish weight gain depends on fish initial weight, water temperature, the fish
growth co-efficient is as prescribed by Goddek [10]:
Wf(t)i= [W1βf
0+ (1 βf)αfeγfTw∆t]
where Wf(g) is the fish weight at a specific time increasing, W0(g) is the
initial fish weight, Twis the water temperature (C), and αf,βfand γfare
species-specific growth-coefficients (αf= 0.0277, βf= 0.4071 and γf= 0.0697),
and idenotes for accumulation of Wfin time (i.e. changing biomass with each
simulation step).
TDS of water depends on fish feed, EC (electrical conductivity) and their
co-relation factor which is different for each fish species:
T DS =F.EC.K E (3)
Water PH depends on hydronium HO3
, nitrates and water temperature.
pH =HO3
Nitrates which is essential for plants and not toxic for fish. It is modeled by the
following equation:
Nitrates(ppm) = Ammonia(N H3)·N itrif ication Coef f icient (5)
The current assumption is to keep water temperature constant. The plant
growth model contains factors of CO2, nutrients, sunlight and oxygen dissolved
in water. We apply a model presented by Akyol [3] extended with factors for
BOD and nitrates.
Xnew = (i, It + 1) + y+β+BOD mg/L (6)
8 A. Ahmed et al.
Fish Weight Ammonia
Plant Weight
Fish Grow
Plant Grow
Light Strength
Rate +
Positive Influence
Negative Influence
Fig. 4: The simulation models variables
Water is re-circulated again and again in our system with water loss because
of evaporation and solid waste removal. We model total water loss in four-week
time as described by Wetzel [31]
where, gh: amount of evaporated water per hour (kg/h), θ= (25 + 19 v) evap-
oration coefficient (kg/m2h), v: velocity of air above the water surface (3 m/s),
A: water surface area (1 m2), S: Dissolved solid quantity removed from system
kg/h, ys: maximum humidity ratio of saturated air (0.51), and yis humidity
ratio air (0.43 kg H2O in kg Dry Air).
5 Results and Empirical Analysis
This section provides results of implementation of the aquaponic system de-
scribed in the previous sections. The results discussed in this section were ob-
tained during a four-week experiment with physical system.
The humidity of our system ranges between 32-51%, room temperature varied
from 24-30 degree Celsius. Fish aquarium water temperature was a little lower
than room temperature. Water temperature was 24-29 degrees Celsius. Humidity
and temperature levels are both in a good range for plant and fish growth. We
have not observed any significant problems due to temperature and humidity
Fish feed was set at 20 grams per day. As shown in Figure 5a, after one week
feed was reduced as the TDS level increases. After another week the feed was
Digital Twin Technology for Aquaponics 9
increase 10% again as the TDS and PH become stable. After the third week the
feed was decreased again as the nitrates are high. Compared with the real fish
weight with simulation as in Figure 5b, actual fish weight gain is lower. Feed
was reduced to keep the ammonia and nitrates level stable.
(a) Fish Feed (b) Fish Weight
Fig. 5: Fish Feed and Fish Weight.
There is very little difference between the PH of physical with digital twin,
as shown in Figure 6a. Actual PH increases in the first two weeks, becomes
stable as the nitrifying bacteria start converting the ammonia into nitrates. The
simulation also predicted PH and TDS both dependent on fish feed and bio-
The total dissolved solids (TDS) is shown in Figure 6. TDS decreases when
the plants start to grow at full speed. TDS is correlated with the amount of food
introduced to the system. In the simulation, TDS was a linear trend, ranging
from 400 to 472 in 4-week time. Fish can thrive with conditions up to 600ppm
TDS. Figure 6b shows maximum TDS is 550ppm, the minimum actual was
389ppm. TDS also decreases as we remove solid waste at the end on each week.
The simulation fails to predict actual nitrates. Actual nitrates rise in weeks
3 and 4 (Figure 7a). It reaches at 32mg/l at the end of week 4. Two plants are
not sufficient to absorb all nitrates from water. As shown in Figure 7b actual
plant growth is greater than expected by the simulated one as the nitrates levels
increases unexpectedly and the plant grows faster. We have also controlled the
plant growth by changing the fish feed rates. This is an effective method to
control plant production in aquaponics system.
6 Conclusion
This paper described implementation and validation of a physical IoT aquaponic
system and a simulated representation. Empirical results showed that some quan-
10 A. Ahmed et al.
(a) Water PH (b) Water TDS
Fig. 6: Water PH and TDS
(a) Nitrate Level (b) Plant Growth
Fig. 7: Nitrate Level and Plant Growth.
tities (e.g. PH and total dissolved solids) were able to be easily estimated in the
simulation but others were more difficult to anticipate accurately in the approach
used such as nitrate levels and growth rates which were underestimated. In fu-
ture work coupling the simulation and real system more closely will enable the
simulation variables to be updated in order to provide more accurate predictions
of the behavior of the system and hence better control functionality.
1. Abdelnour, S., Tartir, A., Zurayk, R.: Farming palestine for freedom (2012)
2. Aishwarya, K., Harish, M., Prathibhashree, S., Panimozhi, K.: Survey on auto-
mated aquponics based gardening approaches. In: 2018 Second International Con-
ference on Inventive Communication and Computational Technologies (ICICCT).
pp. 1377–1381. IEEE (2018)
Digital Twin Technology for Aquaponics 11
3. Akyol, A.: Plant intelligence based metaheuristic optimization algorithms. In: AAr-
tif Intell. pp. 10.1007/s10462–016–9486–6. Rev DOI (2013)
4. Blasch, E., Seetharaman, G., Reinhardt, K.: Dynamic data driven applications
system concept for information fusion. Procedia Computer Science 18, 1999–2007
5. Bubak, M., van Albada, G.D., Dongarra, J.J., Sloot, P.M.A. (eds.): Computational
Science - ICCS 2008, 8th International Conference, Krak´ow, Poland, June 23-25,
2008, Proceedings, Part III, Lecture Notes in Computer Science, vol. 5103. Springer
6. Chhetri, S.R., Faezi, S., Faruque, M.: Digital twin of manufacturing systems. Cen-
ter for Embedded & Cyber-Physical Systems (2017)
7. Diver, S., Rinehart, L.: Aquaponics-Integration of hydroponics with aquaculture.
Attra (2000)
8. Food, F.: agriculture: key to achieving the 2030 agenda for sustainable develop-
ment. Rome: Food and Agriculture Organization of the United Nations (2016)
9. Ghandar, A., Theodoropoulos, G., Zheng, B., Chen, S., Gong, Y., Zhong, M.: A
dynamic data driven application system to manage urban agricultural ecosystems
in smart cities. In: 2018 4th International Conference on Universal Village (UV).
pp. 1–7. IEEE (2018)
10. Goddek, k.: A fully integrated simulation model of multi-loop aquaponics: A case
study for system sizing in different environments. In: Agricultural Systems 171. p.
143154. elsevier (2019)
11. Godfray, H.C.J., Beddington, J.R., Crute, I.R., Haddad, L., Lawrence, D., Muir,
J.F., Pretty, J., Robinson, S., Thomas, S.M., Toulmin, C.: Food security: the chal-
lenge of feeding 9 billion people. science 327(5967), 812–818 (2010)
12. Lasi, H., Fettke, P., Kemper, H.G., Feld, T., Hoffmann, M.: Industry 4.0. Business
& information systems engineering 6(4), 239–242 (2014)
13. Lastiri, D.R., Geelen, C., Cappon, H.J., Rijnaarts, H.H., Baganz, D., Kloas, W.,
Karimanzira, D., Keesman, K.J.: Model-based management strategy for resource
efficient design and operation of an aquaponic system. Aquacultural engineering
83, 27–39 (2018)
14. Liu, J., Dietz, T., Carpenter, S.R., Alberti, M., Folke, C., Moran, E., Pell, A.N.,
Deadman, P., Kratz, T., Lubchenco, J., et al.: Complexity of coupled human and
natural systems. science 317(5844), 1513–1516 (2007)
15. Madey, G.R., Barab´asi, A.L., Chawla, N.V., Gonzalez, M., Hachen, D., Lantz, B.,
Pawling, A., Schoenharl, T., Szab´o, G., Wang, P., et al.: Enhanced situational
awareness: Application of dddas concepts to emergency and disaster management.
In: International Conference on Computational Science. pp. 1090–1097. Springer
16. Mamatha, M., Namratha, S.: Design & implementation of indoor farming using
automated aquaponics system. In: 2017 IEEE International Conference on Smart
Technologies and Management for Computing, Communication, Controls, Energy
and Materials (ICSTM). pp. 396–401. IEEE (2017)
17. Mandap, J.P., Sze, D., Reyes, G.N., Dumlao, S.M., Reyes, R., Chung, W.Y.D.:
Aquaponics ph level, temperature, and dissolved oxygen monitoring and control
system using raspberry pi as network backbone. In: TENCON 2018-2018 IEEE
Region 10 Conference. pp. 1381–1386. IEEE (2018)
18. Manju, M., Karthik, V., Hariharan, S., Sreekar, B.: Real time monitoring of the
environmental parameters of an aquaponic system based on internet of things.
In: 2017 Third International Conference on Science Technology Engineering &
Management (ICONSTEM). pp. 943–948. IEEE (2017)
12 A. Ahmed et al.
19. Munguia-Fragozo, P., Alatorre-Jacome, O., Rico-Garcia, E., Torres-Pacheco,
I., Cruz-Hernandez, A., Ocampo-Velazquez, R.V., Garcia-Trejo, J.F., Guevara-
Gonzalez, R.G.: Perspective for aquaponic systems:omic technologies for microbial
community analysis. BioMed research international 2015 (2015)
20. Mustafee, N., Powell, J.H.: From hybrid simulation to hybrid systems modelling. In:
2018 Winter Simulation Conference, WSC 2018, Gothenburg, Sweden, December
9-12, 2018. pp. 1430–1439 (2018)
21. Onggo, B.S.: Symbiotic simulation system (s3) for industry 4.0. In: Simulation for
Industry 4.0, pp. 153–165. Springer (2019)
22. Onggo, B.S., Mustafee, N., Smart, A., Juan, A.A., Molloy, O.: Symbiotic simulation
system: Hybrid systems model meets big data analytics. In: 2018 Winter Simulation
Conference, WSC 2018, Gothenburg, Sweden, December 9-12, 2018. pp. 1358–1369
23. Pasha, A.K., Mulyana, E., Hidayat, C., Ramdhani, M.A., Kurahman, O.T., Ad-
hipradana, M.: System design of controlling and monitoring on aquaponic based on
internet of things. In: 2018 4th International Conference on Wireless and Telem-
atics (ICWT). pp. 1–5. IEEE (2018)
24. Rakocy, J.E., Masser, M.P., Losordo, T.M.: Recirculating aquaculture tank pro-
duction systems: aquaponicsintegrating fish and plant culture. SRAC publication
454(1), 16 (2006)
25. Rockstr¨om, J., Williams, J., Daily, G., Noble, A., Matthews, N., Gordon, L., Wet-
terstrand, H., DeClerck, F., Shah, M., Steduto, P., et al.: Sustainable intensification
of agriculture for human prosperity and global sustainability. Ambio 46(1), 4–17
26. Ruan, J., Wang, Y., Chan, F.T.S., Hu, X., Zhao, M., Zhu, F., Shi, B., Shi, Y., Lin,
F.: A life cycle framework of green iot-based agriculture and its finance, operation,
and management issues. IEEE Communications Magazine 57(3), 90–96 (2019)
27. Satoh, A.: A hydroponic planter system to enable an urban agriculture service
industry. In: 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE).
pp. 281–284. IEEE (2018)
28. Uhlemann, T.H.J., Schock, C., Lehmann, C., Freiberger, S., Steinhilper, R.: The
digital twin: Demonstrating the potential of real time data acquisition in produc-
tion systems. Procedia Manufacturing 9, 113–120 (2017)
29. Valiente, F.L., Garcia, R.G., Domingo, E.J.A., Estante, S.M.T., Ochaves, E.J.L.,
Villanueva, J.C.C., Balbin, J.R.: Internet of things (iot)-based mobile application
for monitoring of automated aquaponics system. In: 2018 IEEE 10th International
Conference on Humanoid, Nanotechnology, Information Technology, Communica-
tion and Control, Environment and Management (HNICEM). pp. 1–6. IEEE (2018)
30. Vernandhes, W., Salahuddin, N.S., Kowanda, A., Sari, S.P.: Smart aquaponic with
monitoring and control system based on iot. In: 2017 Second International Con-
ference on Informatics and Computing (ICIC). pp. 1–6. IEEE (2017)
31. WETZEL: Encyclopedia of soils in the environment. In: Water Evaporation. pp.
141–183. science direct (2015)

Supplementary resource (1)

... However, this model fails in the presence of control actions, possibly due to the lack of training data with an active controller. A forecasting algorithm for Aquaponics based on empirical biological principle modelling is proposed in [2]. This model is deployed in a small-scale experiment for four weeks. ...
... • Compare the results with a multi-layer perceptron network (MLP) as baseline model. 2 ...
Full-text available
Aquaponic systems provide a reliable solution to grow vegetables while cultivating fish (or other aquatic organisms) in a controlled environment. The main advantage of these systems compared with traditional soil-based agriculture and aquaculture installations is the ability to produce fish and vegetables with low water consumption. Aquaponics requires a robust control system capable of optimizing fish and plant growth while ensuring a safe operation. To support the control system, this work explores the design process of Deep Learning models based on Recurrent Neural Networks to forecast one hour of pH values in small-scale industrial Aquaponics. This implementation guides us through the machine learning life-cycle with industrial time-series data, i.e. data acquisition, pre-processing, feature engineering, architecture selection, training, and model verification.
... The majority of applications of the digital twin concept are in manufacturing. Earlier versions of some of this work was introduced in earlier conference publications, see [24], [4] and [25], with the latter receiving the Best Paper Award in AsiaSim 2019 2 . ...
... Causal loop diagram illustrating relationship between model variables and feedback loops -adapted from[25] ...
Full-text available
There are many pressures on the global food system such as urbanization, climate change, and environmental degradation. Urban agriculture is an approach to producing food inside cities where, globally, more than half the worlds population live. It has been shown to have a range of potential benefits, for instance in reducing waste and logistics costs. Increased uptake of urban farming can even relieve pressure on the natural environment by reducing the burden of production required from farmland by creating space for it to recover from accumulated damage as a result of the use of unsustainable farming practices historically. This article describes an approach for a new type of decision support system suitable for urban farming production. We discuss differences between the requirements and the users of decision support in urban agriculture, and those of ordinary agribusiness enterprises. A case study is performed using a novel technology for urban farming: a cyber-physical implementation of aquaponics is enhanced with adaptive capabilities using a digital twin system and machine learning. Aquaponics is a farming technique that utilizes a harmonious nutrient exchange cycle for growing plants and fish together, while conserving water, and possibly without the need for soil or even sunlight. Empirical results are provided that evaluate the use of data driven decision analytics and a digital twin model to plan production from the aquaponic system during a three month trial. Another set of results evaluate a proposed modelling framework for large scale urban agriculture ecosystems. This concept forms the basis of the suggested approach for an urban farming decision support system that coordinates the activities of many independent producers to target collective goals.
... Water spinach affected the temperature, pH, and oxygen content of the experimental water (Pamula, 2019). Fish can grow in conditions up to 600ppm TDS (Ahmed et al., 2019). Figure 1 shows the maximum TDS was 500ppm, and the minimum value was 430ppm. ...
Full-text available
Aquaponics combines two technologies, recirculating aquaculture systems and hydroponics in a closed system. The nutrients recycled from fish tanks supply nutrients for vegetables grown in hydroponics, however in some cases, the nutrient levels may not be sufficient for the optimal growth and yield of plants. In this study, two experiments were conducted to understand the effects of supplemental organic nutrient solutions on plant growth and yield in climbing perch-water spinach aquaponics. Experiment 1 (Exp.1) was conducted to evaluate the effects of three types of leaf-based organic fertilizers on the growth and yield of water spinach, namely self-extracted organic nutrient solution (OE), and two popular commercial foliar organic fertilizers, Hydro Fulvic (OF1) and TCN HUME (OF2), with the dose of 1%. Exp.1 showed that supplementation with the self-extracted solution significantly increased the growth and yield of water spinach but did not change the quality of water spinach in terms of the Brix values and nitrate residue content compared to the control. However, the self-extracted solution showed less effectiveness than the two commercial fertilizers in this experiment. Therefore, we conducted experiment 2 (Exp.2) to determine the suitable concentration and potential use of this extract for water spinach in aquaponics. The results of Exp.2 indicated that the concentration of 2% was the most economical and effective to provide supplemental nutrients for water spinach in the climbing perch-water spinach system. The study suggests that self-extracted organic nutrient solutions can be effectively used for growing water spinach in aquaponic systems.
... Soil-water Supporting precision irrigation in agriculture, better irrigation planning and water distribution, reduce crop yield losses [54] Soil-water IoT-based water management platform, monitoring water pattern in soil [37] Water Analyze and optimization of aquaponic systems, minimize water waste [85] Irrigation Urban-integrated hydroponic system, integration of forecasting models for better decision-making assistance [73] Irrigation System management and irrigation decision-making integration, water use, global energy and pumping facilities efficiency evaluation, understanding of irrigation system process [57] Water Development of decision support system, enhancement of cyber-physical implementation in aquaponics [86] Table 3. Summary of the digital twin in crop production. ...
Full-text available
Digitalization has impacted agricultural and food production systems, and makes application of technologies and advanced data processing techniques in agricultural field possible. Digital farming aims to use available information from agricultural assets to solve several existing challenges for addressing food security, climate protection, and resource management. However, the agricultural sector is complex, dynamic, and requires sophisticated management systems. The digital approaches are expected to provide more optimization and further decision-making supports. Digital twin in agriculture is a virtual representation of a farm with great potential for enhancing productivity and efficiency while declining energy usage and losses. This review describes the state-of-the-art of digital twin concepts along with different digital technologies and techniques in agricultural contexts. It presents a general framework of digital twins in soil, irrigation, robotics, farm machineries, and food post-harvest processing in agricultural field. Data recording, modeling including artificial intelligence, big data, simulation, analysis, prediction, and communication aspects (e.g., Internet of Things, wireless technologies) of digital twin in agriculture are discussed. Digital twin systems can support farmers as a next generation of digitalization paradigm by continuous and real-time monitoring of physical world (farm) and updating the state of virtual world.
... - [13], 2019 Use IoT and CPS for Aquaponics system management. ...
There is a growing demand to equip Smart Water Networks (SWN) with advanced sensing and computation capabilities in order to detect anomalies and apply autonomous event-triggered control. Cyber-Physical Systems (CPSs) have emerged as an important research area capable of intelligently sensing the state of SWN and reacting autonomously in scenarios of unexpected crisis development. Through computational algorithms, CPSs can integrate physical components of SWN, such as sensors and actuators, and provide technological frameworks for data analytics, pertinent decision making, and control. The development of CPSs in SWN requires the collaboration of diverse scientific disciplines such as civil, hydraulics, electronics, environment, computer science, optimization, communication, and control theory. For efficient and successful deployment of CPS in SWN, there is a need for a common methodology in terms of design approaches that can involve various scientific disciplines. This paper reviews the state of the art, challenges, and opportunities for CPSs, that could be explored to design the intelligent sensing, communication, and control capabilities of CPS for SWN. In addition, we look at the challenges and solutions in developing a computational framework from the perspectives of machine learning, optimization, and control theory for SWN.
Full-text available
Due to the higher level of automation than traditional agricultural systems, Controlled Environment Agriculture (CEA) applications generally achieve better yields and quality crops at the expenses of higher energy consumption. Digital Twin (DT) is considered a technology with the potential to bring CEA to new levels of productivity and sustainability. In this context, a monitoring Digital Twin (mDT) has been developed to provide services for the monitoring of the different subsystems of CEA facilities. By integrating open-source software tools, an architecture was built able to: i) gather different types of data collected from a CEA facility; ii) store the collected data and calculate relevant features from them; iii) locally and remotely display the assessed data. The implemented mDT has the potential to generate a database of CEA data that in future may be utilized by predictive and prescriptive algorithms to suggest actions able to improve the productivity and sustainability of the process.
DOWNLOAD: USE THIS LINK:,70zHZLUT A R T I C L E I N F O Keywords: aquaponics horticulture systems modelling integrated multi-trophic aquaculture aquaculture hydroponics A B S T R A C T Decoupled multi-loop aquaponics systems separate the recirculated aquaculture system (RAS) and hydroponic (HP) units from each another, creating detached ecosystems with inherent advantages for both plants and fish. This gives the advantage of improved crop and fish cultivation in combination, using the minimum resource input. Up to today, the focus of aquaponics systems is mainly on fish culture and treatment of RAS effluent for optimal use in HP, and systems are designed and sized with rule of thumbs of plant growth, evapotranspiration and nutrient needs, while taking the slow responses of RAS dynamics as basis. However, in order to create the optimal fit between RAS and HP, the different systems and differences in time responses of the underlying process need to be considered. Growth of fish and plants happen in hours or days and are slow processes while photosynthesis and transpiration in crops happen in seconds or minutes and are fast processes. As in a closed loop system the main water use is due to plant transpiration, the necessary sizes of system and subsystem depend on plant transpiration. We therefore aimed at creating an aquaponics-sizing simulator based on de-terministic mathematical models and thus transferrable to various circumstances with simple parameterisation. We have combined a full-scale greenhouse simulator with a possible simulation time of min 1 min including HP, greenhouse construction and physics as well as a very detailed plant energy and growth model with a model for a multi-loop aquaponics system including distillation technologies and sumps. To illustrate the quality and wide applicability of our theoretical implementation of a multi-loop aquaponics system in greenhouse conditions we made scenario simulation studies at three different climate zones as sub-arctic cold, moderate and arid subtropical regions (i.e. Faroe Islands [66°N], The Netherlands [52°N], and Namibia [22.6°S]) using the same RAS size while simulating on the fitting HP area. For sizing, we used the element P as the most valuable macro-nutrient for plants. We simulated in a 1-min time steps for a 3-year duration using hourly input climate data for a complete year. Results clearly indicate the importance of transpiration dynamics on system and subsystem sizing, where e.g. the optimal HP size necessary was 11,250 m 2 , 10,250 m 2 and 5250 m 2 (tomato), or 15,750 m 2 , 14,000 m 2 and 9250 m 2 (lettuce), for Faroe Islands, The Netherlands, and Namibia, respectively.
Aquaponics is a technique that combines aquaculture with hydroponics, i.e. growing aquatic species and soilless plants in a single system. Commercial aquaponics is still in development. The main challenge consists in balancing the conditions required for the growth of multiple species, leading to dynamic a system with high complexity. Mathematical models improve our understanding of the complex dynamics in aquaponics, and thus support the development of efficient systems. We developed a water and nutrient management strategy for the production of Nile tilapia (Oreochromis niloticus) and tomato (Solanum lycopersicum) in an existing INAPRO aquaponic demonstration system in Abtshagen, Germany. This management strategy aims for improved water and nutrient efficiency. For this purpose, we developed a system-level mathematical model and simulation. In our simulations, we found that the existing configuration and water management of the Abtshagen aquaponic system results in an excessive amount of water discharged from the RAS. Therefore, sending more nutrient-rich water from fish to plants can help reducing water and fertilizer consumption. However, this water transfer may lead to excess concentrations of some nutrients, which could stress fish, plants or both. For the Abtshagen system, our simulations predicted excess concentrations of total suspended solids (TSS) for the fish, and sodium (Na⁺) and ammonium nitrogen (NH4+-N) for the plants. Furthermore, our simulations predicted excess calcium (Ca²⁺) and magnesium (Mg²⁺) for plants, due to the use of local fresh water with relatively high concentrations of those ions. Based on our simulations, we developed an improved management strategy that achieves a balance between resource efficiency and water quality conditions. This management strategy prevents excess levels of TSS for fish, and Na⁺ and NH4+-N for plants. Under the improved management strategy, simulated water requirements (263 L/kg fish and 22 L/kg tomato) were similar to current commercial RAS and greenhouse horticulture. Simulated fertilizer requirements for plants of N, Ca and Mg (52, 46 and 9 mg/kg tomato, respectively) were one order of magnitude lower than in high efficient commercial closed greenhouse production.