Beruflich Dokumente
Kultur Dokumente
Abstract— This paper presents the design, development, and system is effective, practical, and would enable farmers to
testing of a customizable and cost-effective Weather-Soil Sensor make better informed decisions in their operations.
Station (W-SSS) for use in Precision Agriculture based on high
accuracy sensors, wireless communication, cloud data storage, and II. W-SSS HIGH LEVEL OVERVIEW
computation technology. The W-SSSs operated from July 25, 2018,
to September 15, 2018, using an off-grid power system, Arduino The W-SSS system consists of the hardware needed to
microcontroller, and Wi-Fi connection to the cloud. Sensor data
collect, store, and transmit the data as well as the data
quality was evaluated using several statistical techniques. The data
management to validate, format, and present to the user. A
obtained from the weather-soil stations illustrate the differences in
unique feature of the W-SSS is that it can be configured as a
weather and soil conditions both relative to the local weather station
singular, Super-Node system or as a group of Nodes
as well as those within a field. Knowledge of these differences would
allow a farmer to vary planting densities relative to soil conditions,
communicating with the Super-Node. A block diagram of a
irrigation control, as well as pest/herbicide management.
W-SSS Super-Node and Sensor-Node system is shown in Figs.
1 and 2, respectively.
Keywords --- Super-Node, Sensor-Node, Internet of Things
I. INTRODUCTION
B. Microcontroller
Fig. 3. Power system components
The Arduino Mega 2560, was chosen to interface with the
sensors, Wi-Fi, real time clock, and SD card as it is widely IV. SYSTEM SOFTWARE AND DATA
available and the software easy to use. It has 54 digital I/O, 16 MANAGEMENT
analog inputs, SPI and I2C communication, and regulated 5V
and 3.3V supplies [12]. The individual weather and soil The Arduino Integrated Development Environment (IDE)
sensors were interfaced to the Arduino using a Rugged- was used to write the W-SSS software due to ease of access
Circuits Aussie Shield breakout board with push connectors and availability of open-source libraries [12]. Each sensor
[13]. required the development of a “setup” and a “loop” portion of
code. Fig. 4 shows a generic flow chart for the operation of
C. Power Management each sensor.
The W-SSS Node and Super-Node systems need to operate
independently and unmanned in remote areas for the entire
A. Communication and Data Transmission
growing season. This necessitated an off-grid power system
The W-SSS Sensor Nodes transmit their data to the Super-
Node where the data packets are combined. The aggregated
094
data is communicated to the cloud server using an Adafruit to cover the network entities communication to provide data
model TWNIC1500 Wi-Fi module. The TWNIC1500 is an privacy and data integrity [17-19].
IEEE® 802.11 b/g/n network controller and considered ideal
for IoT applications [16]. If local Wi-Fi is available, this 1) Data Stored Locally in SD Card.
communication is direct, otherwise, a Wi-Fi hot spot is Due to concerns about data loss during the transmission
required (Fig. 5). process, an SD card was used in each W-SSS to store the
aggregated data. An RSA (Rivest, Shamir, and Aleman)
cryptography algorithm was used to encrypt the data saved into
the SD card to prevent unauthorized access. The advantages
of using an RSA cryptography algorithm include 1) RSA is an
asymmetric key with a simple algorithm; 2) low power
consumption; 3) RSA is suitable for any network type [20, 21].
chosen because it is a common crop in the area and prone to determined that the source of error was due to connectivity
weather related diseases such as white mold [22]. During an between the Wi-Fi shield and the internet hotspot. If no
interview conducted on July 11, 2018, Assistant Professor internet connection was available after data collection, the data
Emmanuel Byamukama, extension plant pathologist, South was saved to the SD card but not transmitted to the cloud.
Dakota state University, stated that a diverse weather A future improvement to the data transmission process is
condition, soil properties, and land topographies are a real test the addition of a binary Transmission Confirmation Tag (TCT)
W-SSSs performance. Therefore, the specific sites within this to the end of each data packet. If an internet connection is
field were chosen to assess potential weather variations due to available at the time of transmission, the TCT value is a 1.
minor differences in elevation (Fig. 8). However, if a connection is unavailable during the intended
transmission, the value is a 0. If at a later point in time, a
connection would become available, those data packets which
were not transmitted would be re-transmitted.
Fig. 8. Low elevation deployment station (a) and high elevation deployment B. Data Validation
station (b). Since precision agriculture relies on quality information
collected from a field to make informed decisions, several
B. System Operation and Maintenance statistical techniques were used to assess the validity of the
The W-SSSs operated from July 25, 2018, to September data provided by the W-SSSs.
15, 2018. During this time, each W-SSS recorded ten weather- Data collected from a field may include errors such as
soil parameters every 30 seconds. Data was concurrently noise, drift, and outliers. The typical reasons for these errors
stored internally in an SD card and sent to a server database in include environment effects, power problems, hardware
the cloud. The W-SSSs were visited weekly to assess the status damage, software problems, network problems, and security
of the battery, power management system, the physical attacks [23]. R language is a statistical programming tool that
condition of the system, and to adjust the height and position was used to search for four common types of potential errors:
of the leaf wetness sensor to match the current crop canopy out of range, stuck-at, outliers, and missing values [23, 24].
(Fig. 9).
1) Out-of-Range Fault
Every sensor has a maximum and minimum possible value
that can be measured [23]. For example, the humidity sensor
cannot have a valid output above 100% RH. Table 2 shows
minimum and maximum sensed value from each applied
parameter in the W-SSS. Data values out of the sensing range
were considered an out-of-range error. The data was analyzed
and verified that no sensor recordings for any parameters were
outside of the manufacturer’s specifications.
TABLE 2
Fig. 9. Leaf wetness sensor mounted on a movable arm to enable close MINIMUM AND MAXIMUM VALUES FOR THE APPLIED SENSORS’ PARAMETER
monitoring of crop canopy.
2) Stuck-at Fault radio. However, the specific weather and soil characteristics
Data that becomes “stuck” at a constant value either within vary from region to region. This lack of field-specific
or outside the expected range is generally considered a Stuck- information makes it difficult to make precise decisions related
at fault or constant fault [23]. For this work, a series of data to crop management. The nearest local weather station, KFSD,
that exhibits zero or nearly zero variation for a period of time is located in Sioux Falls, SD and approximately 10 miles from
will be considered as a stuck-at fault [25]. The calculated the field where W-SSS super nodes were deployed. Fig. 11
variance for temperature in randomly selected periods of an compares temperature, relative humidity, and wind speed
hour, day, and week shows values of 0.79, 192.24, and 206.91, information recorded from W-SSS1, W-SSS2, and KFSD.
respectively. Since the variances were greater than zero, this While the data trends are very similar, there are clear
is strong evidence that the sensed data had no stuck-at fault differences in weather conditions. For example, the daily
errors. However, some parameters such as relative humidity, temperature excursions are wider in the soybean field than in
wind speed, sun radiation, soil moisture, and leaf wetness have the city. This is likely due to the thermal mass of the concrete
some constant values by nature at a specific period or at and asphalt in the city of Sioux Falls moderating the
specific weather and soil conditions. For example, the solar temperature (heat island effect).
radiation at night will be zero; yet this would not be considered
a fault. Accordingly, this assessment technique was not
appropriate for these parameters.
3) Outliers
Data which are within the sensor range but lying an
abnormal distance from adjacent data points are considered
outliers [26]. The types of outliers investigated include
Additive, Innovation, Level Shift, and Temporary Change [27,
28]. The statistical functions in R language were used to search
the data set for TC, AO, LS, and IO outliers.
Fig. 10 shows the three TC potential outliers observed in Fig. 11. Comparison of W-SSS1, W-SSS2, and KFSD temperature, relative
humidity, and wind speed.
the temperature data. These potential outliers were a
significant increase or decrease in a temperature value in a D. Site-Specific Data Variations
series compared to the previous value. For example, on August Site specific information especially important for PA is
22, 2018, at 11:00 PM, there was a decrease in temperature lacking from the local weather station. This includes field
from 73.14 °F at index 524 to 56.16 °F at data index 525. Two parameters such as soil moisture, soil temperature, and leaf
potential outliers with a dramatic increase in temperature were wetness. While some stations do provide some of this
observed at exactly 9:00 AM on August 25 and 29. No other information, due to varying soil conditions, this information is
types of outliers were observed. not precise. Furthermore, the conditions within a specific field
can also vary tremendously [30]. While the geographic
distance separating W-SSS1 and W-SSS2 is only about 0.32
miles, their data represent very different field conditions (Fig.
12). The W-SSS1 is located at a higher elevation in the field
which results in lower leaf wetness, lower soil moisture, and
higher soil temperature. Accordingly, the W-SSS2 location
likely receives more rainfall runoff and lower evaporative
losses which results in higher leaf wetness and higher soil
moisture. Knowledge of these differences would allow a
farmer to vary planting densities relative to soil conditions,
irrigation control, as well as pest/ herbicide management.
Fig. 10. Three potential outliers observed in the W-SSS2 temperature data.
VII. CONCLUSIONS [10] H. Kopetz, "Internet of things," in Real-time systems: Springer, 2011,
pp. 307-323.
[11] D. Puri. (2016). IoT-based precision agriculture reduces the
A weather-soil station was developed and successfully guesswork in farming. Available:
deployed for the 2018 growing season. The data obtained from https://www.networkworld.com/article/3151154/internet-of-things/iot-
the weather-soil stations illustrates the differences in weather based-precision-agriculture-reduces-the-guesswork-in-farming.html
[12] Arduino. Arduino MEGA 2560 & Genuino MEGA 2560. Available:
and soil conditions both relative to the local weather station as https://www.arduino.cc/en/Main/ArduinoBoardMega2560?setlang=en
well as those within a particular field. Knowledge of these [13] R. R. CIRCUITS. (2016). MEGA Aussie Shield Pro. Available:
differences, readily available on a cell phone application, are https://www.rugged-circuits.com/news/
expected to facilitate and improve PA. Statistical and machine [14] N. R. E. Laboratory, "PVWatts Calculator," 2018.
[15] P. E. Network. Operation of Lead Acid Batteries. Available:
learning techniques could be integrated into the app for various https://www.pveducation.org/pvcdrom/lead-acid-batteries/operation-
PA applications that can make significant improvements in of-lead-acid-batteries
decision making strategies. [16] Atmel, "ATWINC1500 Wi-Fi Network Controller - Software Design
Guide," PDF 2015, vol. 240.
[17] A. F. B. Federation. (2016). Privacy and Security Principles for Farm
ACKNOWLEDGEMENTS Data. Available: https://www.fb.org/issues/technology/data-privacy/
[18] X. Du and H.-H. Chen, "Security in wireless sensor networks," IEEE
Thanks go to the following for their support: Dr. Wireless Communications, vol. 15, no. 4, 2008.
[19] B. Singh, P. Singh, and V. Dhaka, "Sensor data encryption protocol for
Emmanuel Byamukama, Assistant Professor & SDSU
wireless network security," Global journal of computer science and
Extension Plant Pathologist, Mr. Philip Schumacher, Science technology, 2012.
and Operations Officer at the National Weather Service, Sioux [20] R. Kayalvizhi, M. Vijayalakshmi, and V. Vaidehi, "Energy analysis of
Falls, SD, and Mr. Anthony Bly for allowing the W-SSS to be RSA and ELGAMAL algorithms for wireless sensor networks," in
International Conference on Network Security and Applications, 2010,
operated in his field. pp. 172-180: Springer.
[21] R. L. Rivest, A. Shamir, and L. Adleman, "A method for obtaining
REFERENCES digital signatures and public-key cryptosystems," Communications of
the ACM, vol. 21, no. 2, pp. 120-126, 1978.
[1] B. Kay, "Rates of change of soil structure under different cropping [22] R. Harikrishnan and L. d. J. P. D. Rio, "A logistic regression model for
systems," in Advances in Soil Science 12: Springer, 1990, pp. 1-52. predicting risk of white mold incidence on dry bean in North Dakota,"
[2] D. B. G. Williams, M. J. George, and L. Marjanovic, "Rapid detection vol. 92, no. 1, pp. 42-46, 2008.
of atrazine and metolachlor in farm soils: gas chromatography–mass [23] J. Ravichandran and A. I. Arulappan, "Data validation algorithm for
spectrometry-based analysis using the bubble-in-drop single drop wireless sensor networks," International Journal of Distributed Sensor
microextraction enrichment method," Journal of agricultural and food Networks, vol. 9, no. 12, p. 634278, 2013.
chemistry, vol. 62, no. 31, pp. 7676-7681, 2014. [24] R. C. Team, "R: A Language and Environment for Statistical
[3] P. Schröder et al., "Intensify production, transform biomass to energy Computing," ed: R Foundation for Statistical Computing, Vienna,
and novel goods and protect soils in Europe—a vision how to mobilize Austria, 2017.
marginal lands," Science of The Total Environment, 2017. [25] K. Ni et al., "Sensor network data fault types," vol. 5, no. 3, p. 25, 2009.
[4] M. Glantz, "Guidelines for establishing audits of agricultural- [26] K. Ni et al., "Sensor network data fault types," ACM Transactions on
environmental hotspots," Food and Agricultural Organization of the Sensor Networks (TOSN), vol. 5, no. 3, p. 25, 2009.
United Nations (FAO)2003. [27] IBM®. Outlier types, IBM Knowledge Center. Available:
[5] T. J. Lybbert and D. A. Sumner, "Agricultural technologies for climate https://www.ibm.com/support/knowledgecenter/fr/SS3RA7_15.0.0/co
change in developing countries: Policy options for innovation and m.ibm.spss.modeler.help/ts_outliers_overview.htm
technology diffusion," Food Policy, vol. 37, no. 1, pp. 114-123, 2012. [28] M. Shcherbakov, A. Brebels, N. Shcherbakova, V. Kamaev, O. M.
[6] Y. Kebede, K. Gunjal, and G. Coffin, "Adoption of new technologies in Gerget, and D. Devyatykh, "Outlier detection and classification in
Ethiopian agriculture: The case of Tegulet-Bulga district Shoa sensor data streams for proactive decision support systems," in Journal
province," Agricultural economics, vol. 4, no. 1, pp. 27-43, 1990. of Physics: Conference Series, 2017, vol. 803, no. 1, p. 012143: IOP
[7] J. R. Okalebo, K. W. Gathua, and P. L. Woomer, "Laboratory methods Publishing.
of soil and plant analysis: A working manual second edition," Sacred [29] L. Gruenwald, H. Chok, and M. Aboukhamis, "Using data mining to
Africa, Nairobi, p. 21, 2002. estimate missing sensor data," in Seventh IEEE International
[8] S. Swinton and J. Lowenberg-DeBoer, "Evaluating the profitability of Conference on Data Mining Workshops (ICDMW 2007), 2007, pp. 207-
site-specific farming," Journal of production agriculture, vol. 11, no. 4, 212: IEEE.
pp. 439-446, 1998. [30] S. Malcolm, E. Marshall, M. Aillery, P. Heisey, M. Livingston, and K.
[9] J. M. Barcelo-Ordinas, J.-P. Chanet, K.-M. Hou, and J. García-Vidal, Day-Rubenstein, "Agricultural adaptation to a changing climate:
"A survey of wireless sensor technologies applied to precision economic and environmental implications vary by US region," 2012.
agriculture," in Precision agriculture’13: Springer, 2013, pp. 801-808.