论文信息
论文解读
AI 辅助整理- 方法
- 多传感器自主感知与精准配肥的数字化灌溉施肥一体机,山地蓝莓无土栽培试验。
- 发现
- 该一体机可提升水肥利用效率并降低人工依赖。
- 机会点
- 可延伸研究山地复杂地形下多传感器融合决策与变量施肥灌溉的闭环优化。
论文摘要
研制集成多传感器自主感知与精准配肥的数字化灌溉施肥一体机,在山地蓝莓无土栽培中验证,可提升水肥利用效率并降低人工依赖。
全文
Digital Intelligence in AgricultureDigital Intelligence in Agriculture
http:/ /dx.doi.org/10.62762/DIA.2026.142287
R E S E A RC H A RT I C L E
Development of an Intelligent Fertigation Machine and
Its Application Test in Soilless Cultivation of Mountain
Blueberry
Chunxiang Yang
1,*
1GourmetMore (Beijing) Technology Co., Ltd., Beijing 100081, China
Abstract
Conventional manual fertigation practices are
generally limited by low control precision,
considerable water and fertilizer waste, and
poor adaptability to varied horticultural cultivation
conditions. These limitations create particularly
prominent challenges for high-value cash crops
that are highly sensitive to root-zone substrate
electrical conductivity (EC) and pH dynamics.
To address these gaps, this study developed a
digitally intelligent integrated fertigation system
that integrates multi-sensor autonomous sensing,
precise nutrient ratio regulation, and full-cycle
operational monitoring modules. Systematic
validation of both equipment performance and
field production benefits was carried out via field
plot experiments under typical mountainous
soilless blueberry cultivation conditions. The
test results showed that the developed fertigation
system achieved a control uniformity of 95.28%
for EC and 95.07% for pH. Under the prerequisite
of identical total irrigation volume and total
Submitted: 22 July 2026
Revised:31 August 2026
Accepted:15 September 2026
Published: 09 November 2026
Vol.2,No.4, 2026.
10.62762/DIA.2026.142287
*Corresponding author:
Chunxiang Yang
cxyang369@163.com
nutrient supply across the whole growing season,
the precise control mode (PCM) of the proposed
intelligentfertigationsystemexhibitedsignificantly
higher water use efficiency (WUE) and partial
factor productivity of fertilizer (PFP) than the
conventional simple fertigation management
mode (SFM). Meanwhile, the unit-area yield of
blueberries in the PCM treatment increased by
20.1%,andthecommercialuniformityofindividual
fruit weight was significantly improved. This fully
validated system can well meet the intelligent
production requirements of mountainous soilless
blueberry cultivation and provides a viable
technical solution to support the intelligent
upgrading of local soilless blueberry industries in
Southwest China.
Keywords: intelligent fertigation machine, water-fertilizer
integration, mountain blueberry, soilless cultivation,
equipment performance evaluation.
1 Introduction
Water and fertilizer are the core elements for
crop growth and development, and irrigation and
fertigation are the key production practices that
determine crop yield and quality. According to
Citation
Y ang, C. (2026). Development of an Intelligent Fertigation Machine
and Its Application T est in Soilless Cultivation of Mountain Blueberry.
Digital Intelligence in Agriculture, 2(4), 203–213.
© 2026 by the Author. Published by Institute of
Central Computation and Knowledge. This is an open
access article under the CC BY license (https:/ /creati
vecommons.org/licenses/by/4.0/).
203
Digital Intelligence in Agriculture
statistics from the Food and Agriculture Organization
of the United Nations, the average chemical fertilizer
application rate in global farmland reached 116 kg/ha
and the total annual application volume exceeded 190
million tons in 2023 [1, 2]; meanwhile, agricultural
water use accounts for 72% of global freshwater
withdrawal, and this proportion is still rising with the
expansion of global agricultural production, making
agricultural water shortage an increasingly severe
challenge [1]. Low nutrient use efficiency is widely
prevalent across major global crops [3]. Excessive
water and fertilizer use not only increases agricultural
costs but also poses environmental risks, such as
non-point source pollution. Inefficient use of these
resources has become a major bottleneck to global
agricultural sustainability. Addressing this issue
requires improving nutrient efficiency, optimizing
fertilizer application regimes, and adopting precision
water and fertilizer management systems [1].
Fertigation, as an advanced agricultural practice that
delivers fertilizers directly to the plant root zone along
withirrigationwater,offerssignificantadvantagesover
conventional fertilization practices, chiefly reflected in
the greatly improved efficiency of nutrient delivery
andwaterusage[ 4]. Againstthebackdropofgrowing
constraints on arable land and freshwater resources,
fertigationoffersanintelligent“moreharvestwithless
input”solution,ensuringthateverydropofwaterand
every gram of fertilizer is fully utilized. It represents
an optimal integration of efficiency, sustainability, and
profitability for horticultural production: far beyond a
single agronomic technique, it acts as a transformative
approachthatempowersgrowerstocultivatehealthier
crops, conserve critical agricultural resources, and
achieve better economic returns [5].
With the rapid development of the Internet of
Things and intelligent control technology, intelligent
integrated fertigation technology has become a
research hotspot in smart agriculture, greatly
improving the water and fertilizer use efficiency of
global agricultural production [4, 6]. The intelligent
development of protected agriculture in developed
countries began earlier, and the industrialization
level and technical maturity of intelligent fertigation
machines are highly advanced. As the birthplace
of modern drip irrigation technology, Israel has
extensively deployed drip fertigation systems
for the cultivation of high-value horticultural
crops. In the past decades, research on intelligent
integrated fertigation systems, particularly in
China, has advanced at a remarkable pace. Sun et
al. [7] designed a programmable logic controller
(PLC)-based multi-channel nutrient mixing machine
for greenhouse fertigation. Wu et al. [8] developed
a hybrid PID-fuzzy control algorithm based on an
EC model for greenhouse fertigation systems. Lin
et al. [9] proposed an Internet of Things-based
fertigation management framework for sustainable
precision agriculture. Zhu et al. [ 10] designed a
hybrid optimized backpropagation neural network
PID algorithm for the precise control of fertilizer
flow in an integrated water and fertilizer system. Li
et al. [11] developed a vision-based growth-stage
determination and PLC-based fertigation parameter
invocation system for greenhouse blueberry, enabling
automated stage-specific adjustment of fertigation
parameters. Fertigation equipment in China has seen
substantial progress, yet current systems remain
inadequate for practical production needs—especially
regarding precision fertigation for specific crops and
operational reliability in mountainous regions.
Blueberry demand in China has grown steadily in
recent years. Owing to its unique climate and
altitude, Southwest China’s mountainous region has
become a core production area for late-maturing
blueberries, with the cultivation area expanding
steadily. Soilless cultivation, which offers better
environmental control and superior fruit quality,
is increasingly being adopted for blueberries in
these mountainous areas. Proper nutrient solution
management requires maintaining optimal pH, EC,
andionconcentrations. ThepHofthenutrientsolution
is one of the most important factors affecting nutrient
availability, uptake, and solubility [12]. Compared
with other crops, soilless-cultivated blueberries
impose stricter requirements on the precision of the
water-to-fertilizer ratio and the stability of substrate
pH.
Agricultural production across China’s vast territory
is highly heterogeneous, with diverse crop types,
varied cultivation systems, regionally distinct growing
seasons, and marked differences in infrastructure
and management practices. This diversity calls for
customized, integrated fertigation systems tailored to
different production conditions [13]. Conventional
fertilization equipment generally suffers from poor
regulation precision, which often causes substantial
fluctuationsinECandpH.Blueberryplantsarehighly
sensitive to rhizosphere conditions, and frequent
fluctuations in these parameters directly disrupt
plant metabolism, ultimately causing poor vegetative
growth, reduced yield, and inferior fruit quality.
204
Digital Intelligence in Agriculture
Figure 1. Schematic of the fertigation system working principle.
To tackle these bottlenecks in soilless blueberry
cultivationinSouthwestChina’smountainousregions,
this study developed a digitally integrated fertigation
system that precisely regulates EC and pH. Field
experiments were also conducted to evaluate the
system’s performance, providing a practical basis
for improving fertigation management in mountain
blueberry production.
2 Overall Research and Design of the
Intelligent Fertigation Machine
2.1 Structure of the Fertigation Machine
2.1.1 Hardware Composition
This work developed an automated fertigation
machine with real-time monitoring, which consists
of five modules: the core control unit, the water
supply unit, the fertilizer supply unit, the acid supply
unit, and the monitoring unit. The core control
unit is built around a PLC. The water supply unit
comprises water pump, main pipeline, impurity filter,
andmixed-solutioncontrolvalve. Thefertilizersupply
unit includes multiple fertilizer supply branches, the
corresponding variable-frequency fertilizer supply
pumps, and various fertilizer sources. The acid supply
unitconsistsofacidsupplybranch,variable-frequency
acid supply pump, and acid source. The monitoring
unit is equipped with EC and pH sensors. The overall
schematicofthisintelligentfertigationsystemisshown
in Figure 1.
2.1.2 System Integration and Component Functionality
Water delivery line: The inlet of the water pump
is connected to the water source, and its outlet is
plumbed sequentially to the impurity filter and the
main distribution pipeline for water transmission
across the entire system. A mixed-solution control
valve is installed at the outlet end of the main pipeline
to regulate the discharge of the final water-nutrient
mixture.
Nutrientandacidinjectionlines: Allnutrientsupply
branches and the acid supply branch are connected
to the main pipeline as parallel branches. Each
nutrient supply branch is linked to the corresponding
concentrated fertilizer stock solution tank via an
independent variable-frequency fertilizer injection
pump, which enables simultaneous injection of
different fertilizer stock solutions. The acid supply
branch is connected to the acid source tank through a
variable-frequencyacidinjectionpumptodynamically
adjust the pH value of the mixed nutrient solution.
Monitoring and control loop:On the mixed solution
section of the main pipeline, EC and pH sensors are
installedsequentiallyalongthedirectionofwaterflow.
Bothsensorsarewiredtothecontroller,whichreceives
real-timenutrientconcentrationandpHreadings. The
controller is directly connected to the water pump,
all nutrient injection pumps, the acid injection pump,
and the mixed solution control valve. It adjusts the
operating frequency of each pump based on real-time
monitoring data to regulate the EC and pH of the final
mixed nutrient solution.
205
Digital Intelligence in Agriculture
2.2 Digital Control System Design
2.2.1 Overall Composition of the Controller
The controller consists of four functionally
independent modules, which work together to
achieve closed-loop intelligent control with a clear
division of responsibilities. The data analysis module
is the core processing unit, responsible for receiving
signals and computing control decisions. The data
storage module stores a standard database of planting
parametersforthedifferentgrowthstagesofblueberry
plants. The command output module converts the
control decisions into executable control signals and
transmits them to the actuators. The command input
module supports manual parameter setting and
human intervention. The control schematic of the
intelligent fertigation system controller is shown in
Figure 2.
Figure 2. Control schematic of the intelligent fertigation
system controller.
2.2.2 Module Interconnection and Control Logic
Signal input channel: The EC and pH sensors are
directlywiredtothedataanalysismoduleandtransmit
thecollecteddynamicdatatoitinrealtime. Amanual
command input module is also integrated, allowing
manually set parameters to be directly imported into
the data analysis module.
Data comparison and analysis workflow: The
data storage module is interconnected with the
data analysis module and pre-stores the standard
EC and pH thresholds required for blueberry
growth under different environmental conditions
and crop phenological stages. After receiving
real-time measurement data, the data analysis module
automatically compares the measured values with the
pre-calibrated standard values and outputs targeted
optimized control decisions.
Actuation control output: The control decisions
generated by the data analysis module are transmitted
to the water pump, nutrient injection pumps, and acid
injection pump through the command output module.
These actuating pumps dynamically adjust the flow
rates of water, concentrated nutrient stock solution,
and acid solution in real time, thereby keeping the EC
and pH of the mixed nutrient solution steadily within
the preset target ranges, and precisely matching the
nutrientandpHregulationrequirementsforblueberry
growth under specific environmental conditions. The
operating logic of this integrated intelligent fertigation
system is visualized in Figure 3.
Figure 3. Flow chart of the fertigation operational workflow.
3 Evaluating the Performance of the
Fertigation Machine
3.1 Evaluation of EC Control Uniformity and
Accuracy
The developed intelligent fertigation machine was
activated, and the target EC value was set to 2.0
mS/cm. After the system ran stably for 3 minutes,
five consecutive mixed nutrient solution samples
were collected at the pipeline outlet at 1-minute
intervals, and the EC value of each sample was
measured using a pre-calibrated conductivity meter.
The control uniformity and accuracy of EC were
calculated according to Equations (1)-(4) [14]:
¯x =
∑5
j=1 xj
5 (1)
206
Digital Intelligence in Agriculture
where ¯xis the mean EC value (mS/cm), andxj is the
measuredECvalueofthe j-thmeasurement(mS/cm).
sd =
√∑5
j=1 (xj − ¯x)2
5 − 1 (2)
where sd isthestandarddeviationofthemeasuredEC
values (mS/cm).
v =
(
1 − sd
¯x
)
× 100% (3)
where v is the EC control uniformity (%).
pe =
(
1 −
⏐⏐⏐⏐ ¯x − xrxr ⏐⏐⏐⏐) × 100% (4)
where pe is the EC control accuracy (%), andxr is the
target EC value (mS/cm).
3.2 Evaluation of pH Control Uniformity and
Accuracy
The developed intelligent fertigation machine was
activated, and the target pH value was set to 6.0. After
the system ran stably for 3 minutes, five consecutive
mixed nutrient solution samples were collected at the
pipeline outlet at 1-minute intervals, and the pH value
of each sample was measured using a pre-calibrated
pH meter. The pH control uniformity and accuracy
were calculated according to Equations (5)-(8) [14]:
¯z =
∑5
j=1 zj
5 (5)
where ¯z is the mean of the pH values, andzj is the pH
value of thej-th measurement.
sz =
√∑5
j=1 (zj − ¯z)2
5 − 1 (6)
where sz is the standard deviation of pH.
vz =
(
1 − sz
¯z
)
× 100% (7)
where vz is the pH control uniformity (%).
ph =
(
1 −
⏐⏐⏐⏐ ¯z − zrzr ⏐⏐⏐⏐) × 100% (8)
where ph is the pH control accuracy (%), andzr is the
target pH value.
4 Field Evaluation of Fertigation Modes for
Blueberry Growth and Yield
4.1 Overview of the Blueberry Experimental Site
The experiment was conducted in a multi-span plastic
greenhouse located in the dry-hot valley region of
the Jinsha River, at an altitude of 1,420 m, where
annual sunshine duration exceeds 2,700 hours. The
site is representative of a typical mountain blueberry
cultivationsysteminSouthwestChina. Three-year-old
southern highbush blueberry (Vaccinium corymbosum
L. interspecific hybrid) ‘O’Neal’ plants that were
uniformly vigorous and free of visible pests and
diseases were selected for use in this study. A potted
soilless cultivation system was adopted, with all
plants grown in standardized 40 cm diameter pots
(volume of approximately 38 L), each equipped with
drainage holes to prevent waterlogging. All pots
were filled with the same specifically formulated
substrate (peat:perlite:coconut coir = 4:2:4, v/v),
ensuring uniform physical properties and eliminating
treatment-related differences in water and nutrient
retention. The planting density was 1 m × 2 m
(plant spacing × row spacing), equivalent to 5,000
plants/ha (approximately 333 plants per mu; 1 mu≈
667 m2). Each pot received a water-soluble fertilizer
specifically designed for soilless blueberry production
via one pressure-compensating dripper with a flow
rate of 2.5 L/h. The two treatments differed solely
in their fertigation strategy, while all other routine
management practices—including environmental
control (temperature, humidity, and light), pest and
disease management, and pruning-were kept identical
between treatments. Pollinizer cultivars were evenly
planted along the borders of the experimental area,
accounting for 10% of the total plant number, and
were excluded from yield measurements.
4.2 Field Experimental Design and Treatments
Two fertigation strategies were compared in a
randomized block design with three replicates per
treatment, each replicate containing 30 uniform plants.
Both treatments received identical total irrigation
volumes and total nutrient inputs to ensure that these
factors did not confound the experimental results.
The two treatments differed solely in fertilization
scheduling and application method.
Precise control mode of the intelligent fertigation
machine (PCM): The self-developed dedicated
intelligent fertigation machine was used, which
automatically executed batch operations and
maintained dynamic closed-loop regulation of both
207
Digital Intelligence in Agriculture
EC and pH of the fertilizer solution, requiring
no manual intervention for water-fertilizer ratio
adjustments.
Simple fertigation management mode (SFM): A
manually controlled water-fertilizer operation mode
was adopted. Fertigation was managed according to
local empirical practices. The fertilizer solution was
manually prepared in a mixing tank, and irrigation
events were initiated and terminated by manually
switching valves in the delivery system. Total N, P,
K application rates and total irrigation volume over
the entire growth cycle were recorded and matched
those of the PCM treatment.
4.3 Field Experiment Measurement Indices and
Calculation Methods
Irrigation volume and total fertilizer application were
recorded throughout the experiment. Yield-related
parameters were determined, and both irrigation
water use efficiency and fertilizer use efficiency were
subsequently calculated.
Individual fruit weight: Five uniformly growing
plants were selected per treatment, and 50 fruits were
harvested from each plant at 10 days post color break.
Individual fruit weights were determined using an
electronic balance [15].
Yield determination:The total fruit yield from each
treatment was recorded and expressed as yield per
unit area.
Water use efficiency (WUE):WUE was calculated
using Equation (9) [16, 17]:
WUE = YI (9)
where WUE is the irrigation water use efficiency
(kg/m3), Y istheblueberryyield(kg/ha),and I isthe
total irrigation amount over the entire growth period
(m3/ha).
Partial factor productivity of fertilizer (PFP):PFP is
used to characterize fertilizer use efficiency and was
calculated using Equation (10) [16, 18, 19]:
PFP = YF (10)
wherePFPisthepartialfactorproductivityoffertilizer
(kg/kg), Y is the blueberry yield (kg/ha), andF is
the total nutrient input (N + P2O5 + K2O) during the
entire growth period (kg/ha).
4.4 Statistical Analysis
Statistical analysis and data visualization were
performed using IBM SPSS Statistics 26.0 (IBM Corp.,
Armonk, NY, USA). Differences between treatments
weretestedbyone-wayanalysisofvariance(ANOVA),
and differences were considered significant atP <
0.05.
5 Experimental Results and Analysis
5.1 EC Control Performance of the Fertigation
Machine
The EC of the nutrient solution delivered by the
intelligent fertigation machine was measured five
times at a setpoint of 2.0 mS/cm. The results are
presented in Table 1. The EC control uniformity and
accuracy were 95.28% and 98.10%, respectively. Those
values indicate that the device maintained stable EC
control and complied with the national agricultural
industry standard.
5.2 pH Control Performance of the Fertigation
Machine
The pH of the nutrient solution delivered by the
intelligent fertigation machine was measured five
times at a setpoint of 6.0. The results are presented
in Table 2. The pH control uniformity and accuracy
were 95.07% and 97.83%, respectively, indicating that
the device maintained stable pH control and complied
with the national agricultural industry standard.
5.3 EffectsofFertigationModesonIndividualFruit
Weight and Blueberry Yield
For‘O’Neal’,themedianindividualfruitweightunder
PCM was 2.27 g, which was significantly higher
than the 2.0 g recorded for SFM, indicating that
PCM improved the average individual fruit weight
of blueberries. Regarding data distribution, the
PCM box plot exhibited a narrow interquartile range
and low dispersion, indicating improved fruit size
uniformity. In contrast, the SFM treatment showed
a wider interquartile range and greater dispersion,
reflecting lower uniformity (Figure 4).
Because ‘O’Neal’ blueberries are harvested multiple
times across the growing season, a cumulative
approachwasusedinthisstudy,summingallharvests
over the entire growth cycle and converting the total
to yield per unit area. The yield was 16,000.65 kg/ha
under PCM, compared with 13,320.00 kg/ha under
SFM. This represented a 20.1% increase, and the
difference was statistically significant by analysis of
variance (P < 0.05) (Figure 5).
208
Digital Intelligence in Agriculture
T able 1.EC control uniformity and accuracy of the fertigation machine.
Detection
Index
Number of
Replicates
Average Value
(mS/cm)
Standard
Deviation
(mS/cm)
EC Control
Uniformity
EC Control
Accuracy
EC 5 1.962 0.0926 95.28% 98.10%
T able 2.pH control uniformity and accuracy of the fertigation machine.
Detection
Index
Number of
Replicates
Average Value Standard
Deviation
pH Control
Uniformity
pH Control
Accuracy
pH 5 5.87 0.2895 95.07% 97.83%
Figure 4. Effects of different fertigation modes on
individual fruit weight of blueberries. PCM: precise control
mode of the intelligent fertigation machine; SFM: simple
fertigation management mode.
Figure 5. Effects of different fertigation modes on blueberry
yield. Vertical bars indicate SE, and different letters
indicate significant differences atP < 0.05. PCM: precise
control mode of the intelligent fertigation machine; SFM:
simple fertigation management mode.
PCMappliedahigh-frequency,low-volumefertigation
strategy (214 events in total) to accommodate the
shallow root system of blueberry, whereas SFM
involved only 84 events. This high-frequency
approach minimized fluctuations in substrate EC and
moisture, therebymaintainingamorestableroot-zone
environment and better matching nutrient supply to
plant demand.
Anwar et al. [20] demonstrated that optimizing
the NH+4 -N:NO−3 -N ratio in the nutrient solution
significantly improved the growth, nutrient uptake,
andyieldofsoilless-cultivatedblueberries,confirming
that precise nutrient regulation is essential for
high-yield blueberry production. Feng et al. [21]
showed that increasing fertigation frequency
under alternate partial root-zone drip irrigation
significantly increased tomato yield. The yield
increase observed under precise, high-frequency
fertigation in this soilless blueberry study is consistent
with previous findings across diverse horticultural
crops. These results suggest that a precision
fertigation strategy—combining optimized nutrient
formulation and high-frequency delivery tailored to
rootarchitectureandcropdemand—canimproveboth
fruitqualityandyieldinsoillessblueberryproduction
systems.
5.4 Effects of Fertigation Modes on Water Use
Efficiency of Blueberries
Althoughthetotalirrigationvolumewaskeptconstant
between treatments, WUE differed significantly. The
WUE under PCM was 12.26 kg/m3, compared with
10.21kg/m 3 underSFM,representinga20.1%increase
(Figure 6). This indicates that the high-frequency,
precision-delivery strategy effectively improved
irrigationwateruseefficiencyinthissoillessblueberry
system.
This outcome is in good agreement with previous
findings. Previous studies have shown that precise
management of irrigation water using drip irrigation
combined with soil mulching increases yield and
improves the WUE of lettuce crops [22]. Soilless
cultivation has inherent water-saving advantages,
209
Digital Intelligence in Agriculture
Figure 6. Effects of different fertigation modes on blueberry
WUE. Vertical bars indicate SE, and different letters
indicate significant differences atP < 0.05. PCM: precise
control mode of the intelligent fertigation machine; SFM:
simple fertigation management mode.
leading to faster growth and a dramatic decrease in
water and nutrient use; hydroponics typically uses
at least 90% less water than soil-based methods. In
contrast, in traditional open-field soil systems, much
of the water and nutrients are wasted because only a
small portion reaches the roots and the rest is lost to
local waterways [23]. In terms of irrigation regulation,
optimizing irrigation strategies is also a key approach
for improving WUE. Existing studies have confirmed
thatirrigationfrequencycanaffectrootwaterpotential
by altering the average water content in the root
zone and thereby influence crop growth, and that
an appropriate high-frequency irrigation regime can
significantly improve the water uptake efficiency of
crop roots, simultaneously improving both WUE and
yield [24]. The improvement in WUE achieved by the
PCM treatment in this experiment can be attributed
to the application of the aforementioned water-saving
and efficiency-enhancement principles in blueberry
cultivation.
5.5 Effects of Fertigation Modes on Fertilizer Use
Efficiency of Blueberries
PFP is a key indicator of fertilizer use efficiency,
quantifying the yield per unit of nutrient input.
The total nutrient input was kept constant for both
treatments throughout the growing season, ensuring
that nutrient supply did not confound the results. PFP
was 64.49 kg/kg under PCM, compared with 53.69
kg/kgunderSFM,representingasignificantdifference
(P < 0.05) (Figure 7).
Farnesellietal.[ 25]reportedthat,inprocessingtomato
grown with high nitrogen and water supply, a high
fertigation frequency increased the uptake of fertilizer
nitrogen and promoted crop growth. Silber et al. [26]
Figure 7. Effects of different fertigation modes on blueberry
PFP. Vertical bars indicate SE, and different letters indicate
significant differences atP < 0.05. PCM: precise control
mode of the intelligent fertigation machine; SFM: simple
fertigation management mode.
grew lettuce as a model crop in perlite-filled pots and
found that higher fertigation frequency significantly
improved yield, an effect particularly pronounced
at low nutrient concentrations. Frequent fertigation
enhances plant nutrient uptake through two core
mechanisms: it continuously replenishes nutrients
in the depletion zone near the root interface, and
the higher average water content in the medium
enhances mass flow of dissolved nutrients. This
dual effect compensates for nutrient deficits at low
concentrations, thereby contributing to substantial
yield increases. This experiment indicates that
precise, growth-stage-specific regulation of nutrient
solution concentration and timing, combined with
a high-frequency, low-volume fertigation strategy,
maintainedstablenutrientavailabilityintheblueberry
rhizosphere. Thehigheryieldsachievedwithidentical
nutrientinputwereassociatedwithimprovedfertilizer
use efficiency. These findings are consistent with
previousreportsonhigh-frequencyfertigationinother
horticultural crops.
6 Discussion
6.1 Challenges and Equipment Limitations for
Commercial Blueberry Soilless Culture
Blueberry is a shallow-rooted crop with limited
root absorptive capacity and is highly sensitive to
EC and pH fluctuations in the root-zone substrate.
Most existing fertigation studies have focused on
broadacre field crops, whereas this study specifically
addresses the rhizosphere sensitivity of blueberry in
soilless production. Traditional manual fertigation
often causes nutrient concentration spikes and pH
imbalances, leading to growth inhibition, root
necrosis, and yield losses-a long-standing challenge
210
Digital Intelligence in Agriculture
in large-scale soilless blueberry production [ 27].
Moreover, commercial fertigation machines, typically
designed for field crops, often lack the precision
required for blueberry soilless systems.
6.2 Performance and Suitability of the Intelligent
Fertigation Machine
The intelligent fertigation machine maintained
solution EC and pH within the target ranges without
manual calibration, meeting the agricultural industry
standard for control accuracy and uniformity.
Compared with conventional fertilization equipment,
the developed system achieves faster dynamic
response and higher EC and pH control precision,
making it better adapted to the strict nutrient
management requirements of blueberry soilless
cultivation.
6.3 Comparison of Fertigation Modes and
Mechanisms for Yield and Quality
Improvement
Under equal water and nutrient inputs, PCM
outperformed SFM in water and fertilizer use
efficiencies, yield, and fruit uniformity. The
underlyingmechanismisthattheintelligentfertigation
machinepreciselyregulatesthefertilizerconcentration
and application timing at different growth stages,
keeping the fine fibrous roots of blueberries in
a root-zone environment with a stable nutrient
supply, while greatly reducing water and fertilizer
losses. This allows water and fertilizer supply to
match blueberry demand at different growth stages,
ultimately achieving higher yield and improved
quality at the same input level [28].
6.4 Application Value of the Equipment
Overall,thisintelligentfertigationmachineisdesigned
for specialty crops such as blueberries that are highly
sensitive to pH. It closely addresses the core practical
needs of soilless cultivation, and improves both water
and fertilizer use efficiency and yield per unit area
with water and fertilizer inputs held equal. As the
development of green agriculture requires effectively
reducing the risk of non-point source pollution in
mountain agriculture caused by excessive discharge
of water and fertilizer [29, 30], the application of
this equipment aligns well with green agricultural
development requirements [31, 32].
7 Conclusions
Thisstudydevelopedanintelligentfertigationmachine
capable of precise EC and pH control. Under
identical total irrigation and nutrient inputs, the PCM
treatment significantly improved water and fertilizer
use efficiencies and yield per unit area compared with
the SFM treatment. Additionally, PCM reduced fruit
weightvariability,therebyimprovingcommercialfruit
uniformity. This work provides a technological basis
for the modernization of blueberry production in the
mountainous regions of Southwest China.
Data Availability Statement
Data will be made available on request.
Funding
This work was supported without any funding.
Conflicts of Interest
Chunxiang Yang is affiliated with the GourmetMore
(Beijing) Technology Co., Ltd., Beijing 100081, China.
The author declares that this affiliation had no
influenceonthestudydesign,datacollection,analysis,
interpretation, or the decision to publish, and that no
other competing interests exist.
AI Use Statement
The author declares that no generative AI was used in
the preparation of this manuscript.
Ethical Approval and Consent to Participate
Not applicable.
References
[1] FAO. (2025).The State of the World’s Land and Water
Resources for Food and Agriculture 2025: The potential to
produce more and better. Rome: FAO. [CrossRef]
[2] FAO. (2025).FAOSTAT: Fertilizers by nutrient. Last
update July 11, 2025. Retrieved fromhttps:/ /www.fao.
org/faostat/en/#data/RFN
[3] Liu, J., Wang, H., Penuelas, J., Mou, J.,
Delgado-Baquerizo, M., Sardans, J., ... & Fang,
L. (2025). Global-scale prevalence of low nutrient use
efficiency across major crops.Nature Communications,
16(1), 11036. [CrossRef]
[4] Adamo, T., Caivano, D., Colizzi, L., Dimauro, G.,
& Guerriero, E. (2025). Optimization of irrigation
and fertigation in smart agriculture: An IoT-based
micro-services framework. Smart Agricultural
Technology, 11, 100885. [CrossRef]
211
Digital Intelligence in Agriculture
[5] Incrocci, L., Massa, D., & Pardossi, A. (2017). New
trends in the fertigation management of irrigated
vegetable crops.Horticulturae, 3(2), 37. [CrossRef]
[6] Xing, Y., & Wang, X. (2024). Precise application
of water and fertilizer to crops: challenges and
opportunities. Frontiers in Plant Science, 15, 1444560.
[CrossRef]
[7] Sun, G., Li, X., Wang, X., Li, Y., Chen, M., Zhang, Y., &
Yan, T.(2015).Designandtestingofanutrientmixing
machine for greenhouse fertigation.Engineering in
Agriculture, Environment and Food, 8 (2), 114-121.
[CrossRef]
[8] Wu, Y., Li, L., Li, S., Wang, H., Zhang, M., Sun,
H., Sygrimis, N., & Li, M. (2019). Optimal control
algorithm of fertigation system in greenhouse based
on EC model.International Journal of Agricultural and
Biological Engineering, 12(3), 118-125. [CrossRef]
[9] Lin, N., Wang, X., Zhang, Y., Hu, X., & Ruan, J. (2020).
Fertigation management for sustainable precision
agriculture based on Internet of Things.Journal of
Cleaner Production, 277, 124119. [CrossRef]
[10] Zhu, F., Zhang, L., Hu, X., Zhao, J., Meng, Z., &
Zheng, Y. (2023). Research and design of hybrid
optimized backpropagation (BP) neural network PID
algorithm for integrated water and fertilizer precision
fertilization control system for field crops.Agronomy,
13(5), 1423. [CrossRef]
[11] Li, W., Zhao, J., Xu, H., Wang, C., Liu, X.,
Lou, S., ... & Zou, H. (2026). Development of
a vision-based growth-stage determination and
PLC-based fertigation parameter invocation system
for greenhouse blueberry.Agriculture, 16(15), 1638.
[CrossRef]
[12] Fathidarehnijeh, E., Nadeem, M., Cheema, M.,
Thomas,R.,Krishnapillai,M.,&Galagedara,L.(2023).
Currentperspectiveonnutrientsolutionmanagement
strategies to improve the nutrient and water use
efficiency in hydroponic systems.Canadian Journal of
Plant Science, 104(2), 88-102. [CrossRef]
[13] Li, H., Mei, X., Wang, J., Huang, F., Hao, W., & Li, B.
(2021). Drip fertigation significantly increased crop
yield, water productivity and nitrogen use efficiency
with respect to traditional irrigation and fertilization
practices: Ameta-analysisinChina. AgriculturalWater
Management, 244, 106534. [CrossRef]
[14] Domingues, D. S., Takahashi, H. W., Camara, C. A. P.,
& Nixdorf, S. L. (2012). Automated system developed
to control pH and concentration of nutrient solution
evaluatedinhydroponiclettuceproduction. Computers
and Electronics in Agriculture, 84, 53-61. [CrossRef]
[15] Ehret,D.L.,Frey,B.,Forge,T.,Helmer,T.,&Bryla,D.R.
(2012).Effectsofdripirrigationconfigurationandrate
onyieldandfruitqualityofyounghighbushblueberry
plants.HortScience, 47(3), 414-421. [CrossRef]
[16] Wang, X., & Xing, Y. (2017). Evaluation of the effects
of irrigation and fertilization on tomato fruit yield
and quality: a principal component analysis.Scientific
Reports, 7(1), 350. [CrossRef]
[17] Howell,T.A.(2001).Enhancingwateruseefficiencyin
irrigated agriculture.Agronomy Journal, 93(2), 281-289.
[CrossRef]
[18] Fixen, P., Brentrup, F., Bruulsema, T., Garcia, F.,
Norton, R., & Zingore, S. (2015). Nutrient/fertilizer
use efficiency: measurement, current situation and
trends. Managing water and fertilizer for sustainable
agricultural intensification, 270, 1-30.
[19] Dobermann, A. (2007). Nutrient use efficiency -
measurement and management. In Fertilizer Best
Management Practices: General Principles, Strategy for
their Adoption and Voluntary Initiatives vs Regulations
(pp. 1-28). Paris: International Fertilizer Industry
Association (IFA).https:/ /digitalcommons.unl.edu/agronom
yfacpub/1442/
[20] Anwar, A., Zheng, J., Chen, C., Chen, M., Xue,
Y., Wang, J., ... & Song, S. (2024). Effects of
NH4+-N: NO3–N ratio on growth, nutrient uptake
and production of blueberry (Vaccinium spp.) under
soilless culture.Frontiers in plant science, 15, 1438811.
[CrossRef]
[21] Feng, X., Pu, J., Liu, H., Wang, D., Liu, Y., Qiao, S.,
Lei, T., & Liu, R. (2023). Effect of fertigation frequency
on soil nitrogen distribution and tomato yield under
alternate partial root-zone drip irrigation.Journal of
Integrative Agriculture, 22(3), 897-907. [CrossRef]
[22] Michelon, N., Pennisi, G., Myint, N. O., Orsini, F., &
Gianquinto, G. (2020). Strategies for improved water
use efficiency (WUE) of field-grown lettuce (Lactuca
sativaL.) under a semi-arid climate.Agronomy, 10(5),
668. [CrossRef]
[23] Qubbaj, T., & Shtaya, M. (2022). Effect of different
soillessagriculturemethodsonirrigationwatersaving
and growth of lettuce (Lactuca sativa). Research on
Crops, 23(1), 156-162. [CrossRef]
[24] Segal, E., Ben-Gal, A., & Shani, U. (2006). Root water
uptakeefficiencyunderultra-highirrigationfrequency.
Plant and Soil, 282(1-2), 333-341. [CrossRef]
[25] Farneselli, M., Benincasa, P., Tosti, G., Simonne,
E., Guiducci, M., & Tei, F. (2015). High fertigation
frequency improves nitrogen uptake and crop
performance in processing tomato grown with
high nitrogen and water supply.Agricultural Water
Management, 154, 52-58. [CrossRef]
[26] Silber, A., Xu, G., Levkovitch, I., Soriano, S., Bilu, A.,
& Wallach, R. (2003). High fertigation frequency: the
effectsonuptakeofnutrients,waterandplantgrowth.
Plant and Soil, 253(2), 467-477. [CrossRef]
[27] Pinzon, D. A., Amado, G., Rodriguez, J., & Villagran,
E. (2026). A systematic review of integrated
management in blueberry ( Vaccinium spp.):
technological innovation, sustainability, and practices
in propagation, physiology, agronomy, harvest, and
postharvest.Crops, 6(1), 15. [CrossRef]
212
Digital Intelligence in Agriculture
[28] Tuxun, A., Xiang, Y., Shao, Y., Son, J. E., Yamada, M.,
Yamada, S., ... & Yang, Q. (2025). Soilless cultivation:
precise nutrient provision and growth environment
regulation under different substrates.Plants, 14(14),
2203. [CrossRef]
[29] Hussain, F., Ahmed, S., Naqvi, S. M. Z. A., Awais, M.,
Zhang, Y., Zhang, H., ... & Hu, J. (2025). Agricultural
non-point source pollution: comprehensive analysis
ofsourcesandassessmentmethods. Agriculture,15(5),
531. [CrossRef]
[30] Jarecki, W., Balawejder, M., & Matłok, N. (2025).
Sustainable Fertilization Management Consequences
to Horticultural Crops. Horticulturae, 11(9), 1049.
[CrossRef]
[31] Yang, H., Duan, Y., Wei, Z., Wu, Y., Zhang, C.,
Wu, W., ... & Li, W. (2022). Integrated physiological
and metabolomic analyses reveal the differences in
the fruit quality of the blueberry cultivated in three
soilless substrates.Foods, 11(24), 3965. [CrossRef]
[32] Massa, D., Magán, J. J., Montesano, F. F., & Tzortzakis,
N. (2020). Minimizing water and nutrient losses from
soilless cropping in southern Europe. Agricultural
water management, 241, 106395. [CrossRef]
Chunxiang Yangreceived the Ph.D. degree
from the Institute of Botany, Chinese
Academy of Sciences, Beijing, China, in 2010.
He is currently the Technical Director at
GourmetMore (Beijing) Technology Co.,
Ltd. His research interests include smart
agriculture, fruit quality evaluation, and fruit
processing. (Email: cxyang369@163.com)
213
论文原文与出版信息
Digital Intelligence in Agriculture