AU2019100336A4 - A method for on-line detection of nitrogen, phosphorous and potassium in compost during bio-digestive process - Google Patents

A method for on-line detection of nitrogen, phosphorous and potassium in compost during bio-digestive process Download PDF

Info

Publication number
AU2019100336A4
AU2019100336A4 AU2019100336A AU2019100336A AU2019100336A4 AU 2019100336 A4 AU2019100336 A4 AU 2019100336A4 AU 2019100336 A AU2019100336 A AU 2019100336A AU 2019100336 A AU2019100336 A AU 2019100336A AU 2019100336 A4 AU2019100336 A4 AU 2019100336A4
Authority
AU
Australia
Prior art keywords
meteorological data
humidity
solar irradiance
airflow
electrical conductivity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
AU2019100336A
Inventor
Roshan Karri
Vishy Karri
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Expert 365 Pty Ltd
Original Assignee
Expert 365 Pty Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Expert 365 Pty Ltd filed Critical Expert 365 Pty Ltd
Priority to AU2019100336A priority Critical patent/AU2019100336A4/en
Application granted granted Critical
Publication of AU2019100336A4 publication Critical patent/AU2019100336A4/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01C—PLANTING; SOWING; FERTILISING
    • A01C21/00—Methods of fertilising, sowing or planting
    • A01C21/007—Determining fertilization requirements
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01C—PLANTING; SOWING; FERTILISING
    • A01C3/00—Treating manure; Manuring
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/24—Earth materials
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/24—Earth materials
    • G01N33/243—Earth materials for determining biological parameters concerning composting, biodegradability or bioavailability
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
    • G01N27/02—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating impedance
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
    • G01N27/60—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating electrostatic variables, e.g. electrographic flaw testing
    • G01N27/605—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating electrostatic variables, e.g. electrographic flaw testing for determining moisture content, e.g. humidity
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/24—Earth materials
    • G01N33/246—Earth materials for water content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/70—Services for machine-to-machine communication [M2M] or machine type communication [MTC]

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Soil Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Environmental & Geological Engineering (AREA)
  • Geology (AREA)
  • Environmental Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Remote Sensing (AREA)
  • Pathology (AREA)
  • Immunology (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)

Abstract

A method for use in performing on-line detection of Nitrogen, Phosphorous and Potassium (N,P and K) in compost using vegetable waste in a bio-digestive process, the method being performed using one or more electronic processing devices, the method including: receiving, from at least one set of measurements from ammonium, electrical conductivity, moisture content, airflow, humidity and temperature sensors located in compost; determining whether steady state measurements obtained over a period of time; in response to determining input parameters for calculations required, obtaining, from a meteorological data source, meteorological data for a geographical region corresponding to the area of vegetable waste sourced for a prior time period; determining at least one solar irradiance value for the prior time period based on at least some of the meteorological data; and calculating the N,P and K quantity on-line based on at least one set of the ammonium, electrical conductivity, moisture content, airflow, humidity and temperature and solar irradiance measurements; estimating nitrogen, phosphorous and potassium in three separatecalculations. [506] oNiUTS . Processing unit electrical conductivity moisture content airflow humidity temperature solar irradiance NPUTSNitrogen Phosphorous Potassium Fig. 5C: Neural network flow chart of on-line N, P. and K estimation

Description

A METHOD FOR ON-LINE DETECTION OF NITROGEN, PHOSPHOROUS AND
POTASSIUM IN COMPOST DURING BIO-DIGESTIVE PROCESS
Background of the Invention [0001]
This invention relates to a method used for use in on-line detection of Nitrogen, Potassium and Phosphorous in compost during bio-digestive process of vegetable waste.
Description of the Prior Art [0002]
Composting process has been used for generations in producing useful manure for soil conditioning and nutrient boost. The progress to date in manure production ranged from tradition pile type of set-up to a rapid composting technique carried out in drums. Samples from each of the process undergo a thorough laboratory investigation to see if the nutrients and micro-nutrients meet the standards of compost. The macro nutrients like Nitrogen (hereafter referred as N), Phosphorous (hereafter referred as P) and Potassium (hereafter referred as K) are of immediate attention before exploring the further micro-nutrient metals like Cu, Al, Mg, Mg, Mn and Fe in laboratories. The nutrients in compost vary depending upon the process of production. In this process, the ratio of carbon to other elements is brought into balance, thus avoiding temporary immobilization of nutrients. The key use of adding compost to the soil is that nutrients are slowly released to the soil for subsequent availability to plants. The process of composting is compared with the food digestive process where food is digested in the mouth, stomach and small intestine. The digested food is subsequently absorbed in to the blood stream in the small intestine and excess water is absorbed back into the body in large intestine. In a similar way, the organic matter, in a closed bio-digesting machine, is reduced in volume undergoing varied temperature exposure, rotation, moisture content change, humidity variation, change in carbon to nitrogen ratios without immobilization of nutrients for use as a compost. The challenge with the compost production is that, upon completion of the process, we have little or no control on the nutrients present in the product. A fully automated modern bio-digester with controlled humidity, rotation of the drum, moisture controls and air-flow produces rapid compost without any knowledge of the nutrients during the process of production. The outcome of the process, if does not match the standards, is often discarded.
2019100336 02 Apr 2019
The current methods of composting either using traditional pile-methods or through rapid techniques have no control on the nutrients as they are not measured online and depend solely on the laboratories for post-production tests for usability. With advances in soil science and crop specific nutrient requirements, each of the crop’s nutrients requirements from their inception to harvest are well documented. This includes loss of nutrients from the soil during the harvest for specific crops. This then poses a challenge to precisely recoup the nutrient losses occurred after the harvest without generic refill of nutrients, with chemicals, that inevitably causes nutrient imbalance. Similarly, with soil-cards available for many farms, a soil specific compost is only possible to address precise deficiencies when the nutrients are observed online during the dynamic process of bio-digestion. An online monitoring of nutrients in bio-digestive process can assess live conditions and added ability to interfere in adjusting either carbon content or any other nutrient deficiency via adding appropriate organic additives.
[0003]
Typically, macro-nutrient assessments in soils and compost are categorized by target compound N, P and K and by three predominantly popular namely; chemical, electrical and optical. Emphasis has been placed on technologies that require minimal sample preparation, limited sampling time, little maintenance and infrequent calibration. There are different types of sensors that can be used to sense off-line primary nutrients. Conventional soil NPK testing methods have been generally performed by three steps: sampling, pre-treatment and subsequent chemical analysis. Soil sampling is manually carried out in a field to obtain representative soil samples at a proper depth. There are several published methods that emphasise sampling method. Currently the prior-art of measurement of N, P and K is carried out via three techniques namely; conductivity measurement, optical method, and electrochemical methods to analyse concentration of macro nutrients. In conductivity measurement technique two or three electrodes of same material are immersed in soil samples. The electrode materials used can be silver or copper in order to transmit A.C voltage. The voltage when applied to electrodes in sample another electrode is connected to a multi-meter to measure active current changes. The A.C. voltage results in movements of ion which in turn results in variability of current of soil sample. Use of A.C. voltage avoids neutralization of ions while providing varying conductivity. Variability between electrical conductivity and concentration N, P, and K are observed. As concentration of N,P and K increase, changes in electrical conductivity in
2019100336 02 Apr 2019 electrodes are observed. The change in conductivity is converted into electrical signal where calibration is carried out to convert appropriate voltages. In electrochemical method the sensors constitute ion selective electrodes and ion field effective transistor. Both electrode and transistor detect particular ion from samples using sensor fusion. Different membranes, extraction solutions and multi-target system with varied materials, as field effective transistors, in this method. The last type of soil sensor technology is optical sensor which is based on the interaction between incident light and soil surface properties. The reflected light varies due to the soil physical and chemical properties. Laser Induced Florescence Spectroscopy (LIFS) is an established optical technique where primary nutrient’s molecules absorb radiation at a wavelength within the region of UV and visible region. For commercial purposes Near InfraRed Spectroscopy (NIR) is used where absorption and reflection from primary nutrient molecules is more prominent at wavelengths in the range of lOOOnm - 2200nm. These optical methods while reliable are time consuming and expensive because of which fewer number of samples are often tested for characterising nutrient variability in fields. All the three technologies incorporate quantitative measures of performance where sensing techniques warrant further attention in efforts to develop an on-line in situ NPK sensing system.
[0004]
The reference in this specification to any prior publication (or information derived from it), or to any matter which is known, is not, and should not be taken as an acknowledgment or admission or any form of suggestion that the prior publication (or information derived from it) or known matter forms part of the common general knowledge in the field of endeavor to which this specification relates.
Summary of the Present Invention [0005]
In one broad form an aspect of the present invention seeks to provide a method and apparatus for use in performing on-line detection of detection of Nitrogen, Potassium and Phosphorous in compost during bio-digestive process of vegetable waste, the method being performed using one or more electronic processing devices, the method including: receiving, from at least one electrical conductivity (EC) sensor located in compost, at least one moisture content and temperature measurements of the compost, at least one sensor measuring ammonium content
2019100336 02 Apr 2019 in compost, at least two sensors measuring airflow and humidity; estimating Nitrogen, Potassium and Phosphorous in compost during bio-digestive process of vegetable waste, as three separate calculations, based on the sensor output of solar irradiance from meteorological data source, meteorological data for a geographical region corresponding to the vegetable waste location and time period; and calculating Nitrogen, Potassium and Phosphorous in compost during bio-digestive process of vegetable waste.
[0006]
In one embodiment, the method includes: determining ammonium values using different techniques; determining electrical conductivity (EC), moisture content and temperature on-line values using on-line sensors; determining humidity and airflow using on-line sensors; determining via sensor output of solar irradiance from meteorological data source for the geographical region under consideration and calculating Nitrogen, Potassium and Phosphorous in compost during bio-digestive process of vegetable waste, based on at least in part on the maximum total ammonium, electrical conductivity, moisture content, airflow, humidity and temperature values together with mean solar irradiance of the local of the compost.
[0007]
In one embodiment, at least one ammonium measurement is determined using in-situ sensors and subsequently using the values for calculating N,P and K via separate equations.
[0008]
In one embodiment the method includes obtaining the solar irradiance from meteorological data based on location of the vegetables grown.
[0009]
In one embodiment the method includes obtaining the meteorological data using at least one of: file transfer protocol (FTP); and; an application programming interface (API).
[0010]
In one embodiment the method includes: comparing the solar irradiance with monthly average for the location of the vegetable patch; and determining higher values for subsequent calculations.
2019100336 02 Apr 2019 [0011]
In one embodiment the method includes: receiving a plurality of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature from a plurality of sensors; determining all highest measurements from those plurality of measurements; and identifying those parameters as input parameters for the calculation of Nitrogen, Potassium and Phosphorous in compost during bio-digestive process of vegetable waste in separate equations.
[0012]
In one broad form an aspect of the present invention seeks to provide apparatus for use in performing on-line detection of Nitrogen, Potassium and Phosphorous in compost during biodigestive process of vegetable waste, the apparatus including: at least one sensor for each of the ammonium, electrical conductivity, moisture content, airflow, humidity, temperature and a meteorological data source via one or more communications networks, the one or more electronic processing devices being configured to: receive, from the at least one sensor for each of the ammonium, electrical conductivity, moisture content, airflow, humidity and temperature detection; in response to estimating N,P and K in compost at any given instance: obtaining, from a meteorological data source, meteorological data for a geographical region corresponding to the location of compost for a prior time period.
[0013]
In one embodiment the one or more electronic processing devices are configured to provide an indication of the determined Nitrogen, Potassium and Phosphorous in compost during biodigestive process of vegetable waste over the subsequent time period.
[0014]
In one embodiment the apparatus includes a plurality of ammonium, electrical conductivity, moisture content, airflow, humidity detection sensors, the plurality of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature detection sensors being coupled together via a sensor communication network.
[0015]
2019100336 02 Apr 2019
In one embodiment the apparatus includes: a gateway unit configured to act as a parent node in the sensor communication network; and a plurality of sensor units each including a respective ammonium, electrical conductivity, moisture content, airflow, humidity and temperature sensors and configured to receive the sensor communication network and transfer the ammonium, electrical conductivity, moisture content, airflow, humidity and temperature detection measurements to the one or more electronic processing devices.
[0016]
In one embodiment the one or more electronic processing devices are coupled to the gateway unit and the meteorological data source via the Internet.
[0017]
It will be appreciated that the broad forms of the invention and their respective features can be used in conjunction, interchangeably and/or independently, and reference to separate broad forms is not intended to be limiting.
Brief Description of the Drawings [0018]
Various examples and embodiments of the present invention will now be described with reference to the accompanying drawings, in which: [0019]
Figure 1 is a flow chart of an example of a method for use in both measuring input parameters and determining Nitrogen, Phosphorous and Potassium;
[0020]
Figure 2 is a schematic diagram of an example of a distributed architecture;
[0021] Figure 3 is a schematic diagram of an example of a server processing system;
[0022] Figure 4 is a schematic diagram of an example of a client processing system; and [0023] Figures 5A to 5C are a flow chart of an example of a method and apparatus for use in determining Nitrogen, Phosphorous and Potassium on-line.
2019100336 02 Apr 2019
Detailed Description of the Preferred Embodiments [0024]
An example of a method for use in estimating on-line Nitrogen, Phosphorous and Potassium will now be described with reference to Figure 1.
[0025] The method will typically be performed using one or more electronic processing devices, which may be provided in the form of discrete devices such as servers or personal computers, or shared computer processing resources which may be obtained using Internetbased cloud computing services. The one or more electronic processing devices will typically be coupled to one or more communication networks to allow data to be received or transferred as required to perform the steps of the method.
[0026] In step 100, the method involves receiving, from at least one sensor measurement for ammonium, electrical conductivity, moisture content, airflow, humidity and temperature detection sensors, the plurality of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature detection sensors, embodiments of the method may utilize a plurality of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature detection sensors which may immersed in compost to allow multiple measurements to be obtained.
[0027] Step 110 involves then involves receiving solar irradiance from meteorological data source, meteorological data for a geographical region corresponding to the vegetable waste location. The meteorological data source may be provided by an organisation that provides weather services, such as the Bureau of Meteorology in Australia. Typically, the meteorological data source will facilitate access to meteorological data such as weather observations and forecasts for different geographical regions. This access may be facilitated via the Internet, for instance by using File Transfer Protocol (FTP) or an Application Programming Interface (API). Accordingly, the meteorological data may be readily accessed via a suitable Internet-enabled interface of the meteorological data source.
[0028] In Step 110 the method involves determining one value for the time period tested, as an average, along with meteorological data. The average values for the parameters from [100]
2019100336 02 Apr 2019 may be determined in a variety of different ways, such as by calculating the mean values of the measured parameters. The solar - irradiance value may be directly obtained from the meteorological data. In some cases, the solar irradiance values may be obtained using different sources/techniques should the data for the location is not available for a given time and day at the water source.
[0029] Step 120 Based on the Step 110 along with sensory inputs from ammonium, electrical conductivity, moisture content, airflow, humidity, temperature detection nitrogen content is calculated.
[0030] In step 130, having calculated nitrogen from Step 120 those nitrogen values along with the sensory inputs from ammonium, electrical conductivity, moisture content, airflow, humidity, temperature and solar irradiance are then used to estimate phosphorous.
[0031] Next, step 140 involves calculating the potassium quantities based on nitrogen and phosphorous data collected from [110] - [130] along with the sensory inputs from ammonium, electrical conductivity, moisture content, airflow, humidity, temperature and solar irradiance.
[0032] Accordingly, nitrogen, phosphorous and potassium quantities can be determined without the need for chemical, electrical, optical or any other time-consuming methods cited.
[0033] It should be noted in particular that the use of meteorological data for the time period to determine the solar irradiance value will mean that the vegetable waste has had an exposure of such irradiance over a period.
[0034]
Further optional implementation features of the method will now be described.
[0035]
As mentioned above, the solar irradiance value may be determined in different ways, and thus in some implementations, the method may include determining a plurality of solar irradiance values using different techniques, determining a maximum solar irradiance value from the plurality of solar irradiance values; and then calculating the N, P and K based at least in part on the maximum solar irradiance value. This may provide a more conservative approach to ensure the primary nutrients is calculated based on a highest solar irradiance scenario, and thus avoid
2019100336 02 Apr 2019 the situation where a solar irradiance calculation based on a particular set of parameters might not accurately model the full extent of solar irradiance in certain circumstances. The use of a maximum solar irradiance insures possibility of under-estimating nutrients which has a higher risk of inhibiting water quality.
[0036]
Implementations of the method may involve calculating solar irradiance values using the meteorological data, for instance by using known calculation methods such as the linear regression (LR), Angstrom-Prescott-Page (APP) and the artificial neural network (ANN) models.
[0037]
For each of the above three models the basic dataset for a given location encompass solar radiation (H), minimum and maximum temperatures (Tmin and Tmax), total rainfall and evaporation (Lr and Le), and sunshine duration (S) over a period of time. A comprehensive dataset is available for many meteorological sites to get the monthly averages. This dataset is also important for ANN training and testing.
[0038]
The linear regression methods (LR) involves the following methodology:
The monthly average daily extra-terrestrial solar radiation, Ho, on a horizontal surface can be calculated from the following equation (Elminir et al., 2007):
x 3600 z
Ho =-—-Iok (cosrpcosSsinti) πω
180 where Io is the solar constant, k is the eccentric correction factor of the earth’s orbit, φ is the latitude of the location (degrees), δ is the solar declination angle (degrees) and ω is the sunset hour angle (degrees). The currently accepted and commonly used Io value is set at 1367 W/m , which is recommended by the World Radiation Centre (Montero et al., 2009; Page, 1986; Stine, 1985). The eccentric correction factor k for each day can be calculated (Yorukoglu and Celik, 2006):
/360d„ k = l + 0.033cos ——\ 365
2019100336 02 Apr 2019 where dn is the day number counted from beginning of the year (where dn = 1 for 1st of January).
The declination angle δ and sunset hour angle ω for each day of the year can be calculated below (Cooper, 1969; Luque and Hegedus, 2003):
δ = 23.45sin
360 x (284 + dnj 365 ω = cos 1(—ΐαηφΐαηδ)
Lastly, the maximum possible sunshine duration, So, for each day is calculated from (Soler and Gopinathan, 1994):
So = is
To gauge the accuracy of the models, the (RMSE) was used.
Linear Regression (LR) Analysis
Having established the values from mathematical equations above for each day, the averages were obtained which forms the linear regression model shown below:
S
7/ aTmin + bTmax + cLr + dLe + @Hq + f — H ff where a to g are regression coefficients, to be determined empirically.
[0039]
On the other hand, the Angstrom-Prescott-Page (APP) method for calculating solar irradiance can be expressed using the formula:
H s — = a + b —
Hq so
2019100336 02 Apr 2019 where a and b are the empirical (or Angstrom) coefficients. The coefficient a can be interpreted as the fraction of the monthly average solar radiation (H/Ho) entering the atmosphere when there is a complete cloud cover (Ahmad and Tiwari, 2011). The second coefficient b defines the rate of change of H/Ho with respect to the sunshine duration ratio (S/So). It is an index of the latitudinal variation (Ahmad and Tiwari, 2011). To determine the values for coefficients a and b, the plot clearness index (H/Ho) vs. sunshine duration ratio (S/So) is plotted to get a linear trend-line.
[0040]
The OLL network was proposed and developed by Ergezinger and Thomsen. This method is based on the linearization of the activation function, thus leading to a linear optimization problem in each layer. The error made when linearizing the activation function is accounted for by introducing a penalty term. This penalty term, whose influence is varied, is to maintain optimum convergence for the network. The OLL neural network is then optimized in an iterative procedure, where for each iteration, the corresponding weights are optimized by solving a set of linear equations. It uses the
Ligure below shows a basic OLL neural network structure. Inputs Xi are connected to the hidden layer with connect weights ra; and the hidden neuron are connected to the output neurons with connection weights Sba- The b neurons in the output layer have a pure linear activation function and hidden neurons have a sigmoid activation function. The training algorithm for the OLL model described below:
Figure AU2019100336A4_D0001
2019100336 02 Apr 2019
Optimization Layer-by-Layer ANN Architecture
Step 1: Initialization
Initial values for the weights R and S, where R and S are the weight vectors between the hiddeninput and output-hidden layers respectively, penalty constant μ and the number of iterations are defined. Weight vectors R and S are to be optimized in order to minimize the error function.
Step 2: Optimization of Output Layer Weights
The optimum weight for S, s°ptimum, is obtained using:
optimum = A~l · b with ^ = ΣΖ/Ζ/ = 0,..., rt
P=1 b = ^zftp a = 0,..., A
P=1 where P is the total number of training data, za p and z,p are the scalar outputs of the hidden neurons of training data p and tp is the target output value.
Update the weights S and calculate the RMS error using below:
ErrOrRMS =
P κ , ,,
ΣΣΟ/’-λ) p=l A=1
PK where K is the total number of output neurons, t|<p is the target output value for neuron k and training data p and yi<p is the network output value for training data p.
Step 3: Optimization of Hidden Layer Weights
The new updated weight R is then defined as Rtest, as shown:
p optimum _
2019100336 02 Apr 2019 where for a/h
X 1 X 1 I linearized I linearized | A = 2^2JfiSba kX>nSbh /J p=l b=l wherei,m - 0,...,1 h = 0,...,A fora - h
P P ~ / v \ _ X 1 X 1 I linearized | linearized | linearized ~ / i / i x^i^ba f^m^bh /+ ~~ $ba /7-1 ό-l L A where Lm -0,...,1 h-0,...,A x{x and p=l b=l where m = 0,...,/ h = 0,..., A where Sba lmeanzed and Sbh'meanzed are the linearized weights from neuron b of the output layer to neurons a and h in the hidden layer (of training data P), X.Aa is the second derivative of the activation function XAa, Sba and Sbh are the connection weights between the output-hidden layer.
Once AR°ptimumis obtained, the new update weight can be defined as:
_j^old | ^j^optimum
Step 4: Test for Completion
RMS error, ERMstest, was then calculated comparing the Rtest matrix with S or s°ptimum matrices calculated in Step 3.
a. ΕκμΓ1<Ε
The hidden layer weight matrix R is updated R = Rtest. Decrease the influence of the penalty term by decreasing μ. Proceed to Step 5.
b. Erms1651 > E
Increase the influence of μ and repeat Step 4a.
2019100336 02 Apr 2019
Step 5: Process Termination
If RMS error solar radiation is not within the desired range, repeat Step 2, else the training process is ceased.
[0041]
It will thus be appreciated that calculation of the solar irradiance value using the any of the three methods will require access to meteorological data including observations of a range of different measurements including the maximum temperature, the minimum temperature, the rain fall and evaporation.
[0042]
Alternatively, or additionally, the solar irradiance value may be determined based on a value calculated by the meteorological data source and included in the meteorological data. As mentioned above multiple techniques can be used and a highest value may be used for calculating the N, P and K.
[0043]
In order to more specifically account for compost in the N,P and K on-line calculation, the method may include determining a solar irradiance value for the particular location of the compost along with ammonium, electrical conductivity, moisture content, airflow, humidity and temperature.
[0044]
In particular, this may involve determining nitrogen from OLL network. In one example, the method may include determining, using ammonium, electrical conductivity, moisture content, airflow, humidity and temperature quantities in accordance with the identification of the parameters for initial calculation of nitrogen and subsequent calculations of phosphorous and potassium.
[0045]
2019100336 02 Apr 2019
It should be appreciated that the particular set of compost data that is stored may depend on the specific techniques used for determining the solar irradiance on vegetables and their waste which results in compost value and/or the N, P and K. In any event, the water N, P and K data may be stored in a database or the like and in some examples may be organised into tables.
[0046]
It will be appreciated that the nitrogen, phosphorous and potassium will be estimated using three separate equations as shown in subsequent text.
[0047]
With regard to the meteorological data, which is used for at least determining the solar irradiance value, this may be obtained based on location data for the compost. For example, a geographical location for a particular site to which this method is to be applied may be used to obtain meteorological data corresponding to that location. In some cases, meteorological data may only be available for neighbouring regions, and the method may either use meteorological data for the closest region or may use averaged values of the meteorological data for more than one neighbouring region if desired.
[0048]
Particular implementations of the method may include obtaining the meteorological data using file transfer protocol (FTP) or an application programming interface (API). The particular technique used for accessing the meteorological data will largely depend on the techniques supported by the meteorological data source.
[0049]
The specific types of meteorological data that may be obtained and used in the method include a relative humidity observation, a maximum temperature observation, a minimum temperature observation, an air temperature observation, a soil surface temperature observation, an atmospheric pressure observation, and a solar radiation exposure observation. The aforementioned observations can support the calculation of evapotranspiration values using the Priestly Taylor method or the Turc method as discussed above, but it should be appreciated that
2019100336 02 Apr 2019 not all of these need to be obtained in all implementations of the method. On the other hand, additional types of meteorological data may also be obtained to support the use of other techniques or for providing extended functionalities.
[0050]
As mentioned above, solar irradiance value may be obtained directly as part of the meteorological data. This can be useful to allow comparisons to the values derived from other techniques, but it should be understood that this is not essential.
[0051]
In another aspect, an apparatus may be provided for use in performing on-line detection of N,P and K for a particular compost. The apparatus may include at least one sensor for each of the ammonium, electrical conductivity, moisture content, airflow, humidity and temperature and one or more electronic processing devices coupled to the at least one or more of the above sensors and a meteorological data source via one or more communications networks. In this regard, the one or more electronic processing devices will be configured to perform the method as described above.
[0052]
In some implementations, the one or more electronic processing devices may be configured to provide an indication of the calculated N,P and K via app.
[0053]
As mentioned above, a plurality of sensors may be used, and in this respect the apparatus may include the plurality of sensors, which may be coupled together via a sensor communication network. In one example, the apparatus may include a gateway unit configured to act as a parent node in the sensor communication network and a plurality of sensor units. Each sensor unit may include a respective ammonium, electrical conductivity, moisture content, airflow, humidity and temperature sensors and be configured to act as a child node in the sensor communication network. The gateway unit may in turn be configured to receive measurements from the sensor units and transfer the moisture measurements to the one or more electronic processing devices.
2019100336 02 Apr 2019 [0054]
The one or more electronic processing devices may be coupled to the gateway unit and the meteorological data source via the Internet. In one specific embodiment, the one or more electronic processing devices may be provided using a cloud computing system and the meteorological data source may be accessed via an Internet API.
[0055]
In one example, the process is performed by one or more processing systems operating as part of a distributed architecture, an example of which will now be described with reference to Figure 2.
[0056]
In this example, the arrangement includes a number of processing systems 201, 203 along with gateway and sensor units 205, 207, each interconnected via one or more communications networks, such as the Internet 202, and/or a number of local area networks (LANs) 204.
[0057]
It will be appreciated that the configuration of the networks 202, 204 are for the purpose of example only, and in practice the processing systems 201, 203 and gateway and sensor units 205, 207 can communicate via any appropriate mechanism, such as via wired or wireless connections, including, but not limited to mobile networks, private networks, such as an 802.11 networks, the Internet, LANs, WANs, or the like, as well as via direct or point-to-point connections, such as Bluetooth, Zigbee or the like.
[0058]
The nature of the processing systems 201, 203 and their functionality will vary depending on their particular requirements. In one particular example, the processing systems 201, 203 represent servers (such as for determining the N,P and K) and clients (for allowing bio-digesting
2019100336 02 Apr 2019 companies processing waste in various geographical positions to monitor N,P and K processes or updating data), although this is not essential and is used primarily for the purpose of illustration.
[0059]
An example of a suitable processing system 201 is shown in Figure 3. In this example, the processing system 201 includes an electronic processing device, such as at least one microprocessor 300, a memory 301, an optional input/output device 302, such as a keyboard and/or display, and an external interface 303, interconnected via a bus 304 as shown. In this example the external interface 303 can be utilised for connecting the processing system 201 to peripheral devices, such as the communications networks 202, 204, databases 211, other storage devices, or the like. Although a single external interface 303 is shown, this is for the purpose of example only, and in practice multiple interfaces using various methods (e.g. Ethernet, serial, USB, wireless or the like) may be provided.
[0060]
In use, the microprocessor 300 executes instructions in the form of applications software stored in the memory 301 to perform required processes, such as communicating with other processing systems 201, 203 or the gateway and/or sensor units 205, 207 depending on the sensor network topology. Thus, actions performed by a processing system 201 are performed by the processor 300 in accordance with instructions stored as applications software in the memory 301 and/or input commands received via the I/O device 302, or commands received from other processing systems 201, 203. The applications software may include one or more software modules, and may be executed in a suitable execution environment, such as an operating system environment, or the like.
[0061]
Accordingly, it will be appreciated that the processing systems 201 may be formed from any suitable processing system, such as a suitably programmed computer system, PC, web server, network server, or the like. In one particular example, the processing system 201 is a standard processing system such as a 32-bit or 64-bit Intel Architecture based processing system, which executes software applications stored on non-volatile (e.g., hard disk) storage, although this is
2019100336 02 Apr 2019 not essential. However, it will also be understood that the processing systems 201 could be or could include any electronic processing device such as a microprocessor, microchip processor, logic gate configuration, firmware optionally associated with implementing logic such as an FPGA (Field Programmable Gate Array), or any other electronic device, system or arrangement.
[0062]
As shown in Figure 4, in one example, the processing systems 203 include an electronic processing device, such as at least one microprocessor 400, a memory 401, an input/output device 402, such as a keyboard and/or display, and an external interface 403, interconnected via a bus 404 as shown. In this example the external interface 403 can be utilised for connecting the processing system 203 to peripheral devices, such as the communications networks 202, 204, databases, other storage devices, or the like. Although a single external interface 403 is shown, this is for the purpose of example only, and in practice multiple interfaces using various methods (e.g. Ethernet, serial, USB, wireless or the like) may be provided.
[0063]
In use, the microprocessor 400 executes instructions in the form of applications software stored in the memory 401 to perform required processes, for example to allow communication with other processing systems 201, 203. Thus, actions performed by a processing system 203 are performed by the processor 401 in accordance with instructions stored as applications software in the memory 402 and/or input commands received from a user via the I/O device 403. The applications software may include one or more software modules, and may be executed in a suitable execution environment, such as an operating system environment, or the like.
[0064]
Accordingly, it will be appreciated that the processing systems 203 may be formed from any suitable processing system, such as a suitably programmed PC, Internet terminal, lap-top, handheld PC, smart phone, PDA, tablet, or the like. Thus, in one example, the processing system 203 is a standard processing system such as a 32-bit or 64-bit Intel Architecture based processing system, which executes software applications stored on non-volatile (e.g., hard disk) storage, although this is not essential. However, it will also be understood that the processing systems
2019100336 02 Apr 2019
203 can be any electronic processing device such as a microprocessor, microchip processor, logic gate configuration, firmware optionally associated with implementing logic such as an FPGA (Field Programmable Gate Array), or any other electronic device, system or arrangement.
[0065]
It will also be noted that whilst the processing systems 201, 203 are shown as single entities, it will be appreciated that this is not essential, and instead one or more of the processing systems
201, 203 can be distributed over geographically separate locations, for example by using processing systems provided as part of a cloud-based environment.
[0066]
In a preferred implementation, the processing systems 201 may be provided as part of a cloud computing service and will communicate with other elements of the arrangement via the Internet
202. The use of other processing systems 203 in the form of client devices is not essential to the method, but in practice will be advantageous to allow users such as vegetable markets, waste processing sites or the like to monitor the N, P and K status for a site. Furthermore, users can interact with the processing systems 201 or data stored on the database 211 to update data for use in the method, such as the input data or N, P and K data, if necessary.
[0067]
The gateway and sensor units 205, 207 may be provided as specialised versions of the processing systems 203 as shown in Figure 4, whereby the external interfaces 403 include dedicated sensor interfaces for interfacing with respective sensors along with network interfaces as required for the particular sensor network topology. For instance, the gateway unit 205 may differ from the sensor units 207 in terms of the particular network connectivity provided. The gateway unit 205 may include external network connectivity for allowing communications with the processing systems 201 via the Internet or any other external network, along with internal network connectivity for enabling communications within a localised sensor network, such as by
2019100336 02 Apr 2019 using Zigbee or any other suitable networking protocol. On the other hand, the sensor units 2017 may only include internal network connectivity.
[0068]
Since the gateway and sensor units 205, 207 may need to be deployed in remote locations these may include localised power sources such as a solar panel and rechargeable batteries. To conserve power, the microprocessor 400 and other hardware used in the gateway and sensor units 205, 207 may be selected for energy efficiency.
[0069]
However, it will be appreciated that the above described arrangement is shown as an example only, and numerous other configurations may be used.
[0070]
A detailed example of a method for use in on-line detection of N, P and K will now be described with regard to the flow chart of Figures 5A to 5B.
[0071]
In this particular example, it is assumed that the main data processing functionalities of this method are provided as part of a cloud computing service which is able to communicate with meteorological data services and gateway and sensor units having respective sensors via the Internet. This example will illustrate a typical loop of N, P and K calculations which may be carried out periodically and potentially only at predetermined times of the day.
[0072]
As an initial process, the method will involve checking the compost at step 500. This may include accessing a closed chamber of a bio-digesting machine’s particular information regarding coordinates, date, time, status of machine on/of. If the machine status is inactive the method may proceed no further, however if the machine status is active a determination may be made on whether the machine status should be changed to inactive.
2019100336 02 Apr 2019 [0073]
Assuming machine status is active, type of waste source such as vegetables, municipal waste, mix of green waste and fruit waste, mix of kitchen waste, paper, cardboard and catering waste, selection should also be made at next step [501] at the field status.
[0074] ammonium, electrical conductivity, moisture content, airflow, humidity and temperature measurements will be received at step 502, and in the event that these are received for multiple sensors in the same compost, these may be processed by averaging or taking a maximum measurement.
[0075]
At step 503 based on the sensory input and steady state collection, ensure the steady quantitative collection of the process parameters to avoid large variability.
[0076]
At [504] meteorological data will be obtained for the day. In this example, the meteorological data may be obtained from three separate meteorological data sources via Internet APIs.
[0077]
The maximum value of the solar irradiance/radiation data may be taken after processing the three models namely: Linear regression, APP and Al. The data is sent to the could at [506] [0078]
Moving on to step 507, the method may then include calculation of nitrogen in the cloud as function of ammonium, electrical conductivity, moisture content, airflow, humidity, temperature along with the solar irradiance obtained from [504],
2019100336 02 Apr 2019 [0079]
Moving on to step 508, the method may then include parallel calculation of phosphorous in the cloud as function of ammonium, electrical conductivity, moisture content, airflow, humidity, temperature along with solar irradiance obtained from [504] and nitrogen from [507].
[0080]
Moving on to step [509], the method may then include another parallel calculation of potassium in the cloud as function of ammonium, electrical conductivity, moisture content, airflow, humidity, temperature along with solar irradiance obtained from [504] and nitrogen from [507] and phosphorous from step [508].
[0080]
Throughout this specification and claims which follow, unless the context requires otherwise, the word “comprise”, and variations such as “comprises” or “comprising”, will be understood to imply the inclusion of a stated integer or group of integers or steps but not the exclusion of any other integer or group of integers.
[0081]
Persons skilled in the art will appreciate that numerous variations and modifications will become apparent. All such variations and modifications which become apparent to persons skilled in the art, should be considered to fall within the spirit and scope that the invention broadly appearing before described.

Claims (10)

1) A method for use in performing on-line measurement of nitrogen, phosphorous and potassium for a compost made from vegetable waste in a bio-digester, the method being performed using one or more electronic processing devices, the method including:
a) receiving, from one set of combined measurement of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature.
b) in response to sensory output in determining on-line nitrogen, phosphorous and potassium for a compost:
i) obtaining, from a meteorological data source, meteorological data for a geographical region corresponding to the location of compost;
ii) determining at least one solar irradiance value for the prior time period, of the vegetable sourced region, based on at least some of the meteorological data; and
2) A method according to claim 1, wherein the method includes:
a) determining a plurality of solar irradiance values using different techniques;
b) determining a maximum solar irradiance value from the plurality of solar irradiance values; and
c) calculating the nitrogen as functions of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature based at least in part on the maximum solar irradiance value.
d) calculating the phosphorous as functions of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature based at least in part on the maximum solar irradiance value and nitrogen.
e) calculating the potassium as functions of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature based at least in part on the maximum solar irradiance value, nitrogen and phosphorous.
3) A method according to any one of claims 1 and 2, wherein at least one solar irradiance value calculated which induce;
a) Solar irradiance value calculated using the meteorological data using regression analysis (RA) method.
b) Solar irradiance value calculated using the meteorological data using AngstromPrescott-Page (APP) method; and
c) Solar irradiance value calculated using the Artificial Neural Network Method (ANN).
d) and solar irradiance value calculated by the meteorological data source and included in the meteorological data.
2019100336 02 Apr 2019
4) A method according to any one of claims 1 to 3, wherein the method includes obtaining the meteorological data based on location data for the compost.
5) A method according to any one of claims 1 to 4, wherein the method includes obtaining the meteorological data using at least one of:
a) file transfer protocol (FTP); and;
b) an application programming interface (API).
6) A method according to any one of claims 1 to 5, wherein the meteorological data includes at least one of:
a) A minimum temperature observation;
b) a maximum temperature observation;
c) a solar radiation exposure observation.
7) Apparatus for use in performing on-line N,P and K estimation for a compost, the apparatus including:
a) at least one sensor measurement for ammonium, electrical conductivity, moisture content, airflow, humidity and temperature; and
b) one or more electronic processing devices coupled to the at least one sensor for ammonium, electrical conductivity, moisture content, airflow, humidity, temperature and a meteorological data source via one or more communications networks, the one or more electronic processing devices being configured to:
i) receive, from the at least one ammonium, electrical conductivity, moisture content, airflow, humidity and temperature measurement;
(a) the at least one solar irradiance value.
(b) estimating nitrogen, phosphorous and potassium.
8) Apparatus according to claim 6 or claim 7, wherein the apparatus includes a plurality of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature sensors, the plurality of ammonium, electrical conductivity, moisture content, airflow, humidity and temperature sensors being coupled together via a sensor communication network.
9) Apparatus according to claim 8, wherein the apparatus includes:
a) a gateway unit configured to act as a parent node in the sensor communication network; and
2019100336 02 Apr 2019
b) a plurality of sensor units each including a respective ammonium, electrical conductivity, moisture content, airflow, humidity and temperature sensors and configured to act as a child node in the sensor communication network, the gateway unit being configured to receive measurements from the sensor units and transfer the moisture measurements to the one or more electronic processing devices.
10) Apparatus according to claim 9, wherein the one or more electronic processing devices are coupled to the gateway unit and the meteorological data source via the Internet.
AU2019100336A 2019-04-02 2019-04-02 A method for on-line detection of nitrogen, phosphorous and potassium in compost during bio-digestive process Active AU2019100336A4 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2019100336A AU2019100336A4 (en) 2019-04-02 2019-04-02 A method for on-line detection of nitrogen, phosphorous and potassium in compost during bio-digestive process

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
AU2019100336A AU2019100336A4 (en) 2019-04-02 2019-04-02 A method for on-line detection of nitrogen, phosphorous and potassium in compost during bio-digestive process

Publications (1)

Publication Number Publication Date
AU2019100336A4 true AU2019100336A4 (en) 2019-05-09

Family

ID=66344415

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2019100336A Active AU2019100336A4 (en) 2019-04-02 2019-04-02 A method for on-line detection of nitrogen, phosphorous and potassium in compost during bio-digestive process

Country Status (1)

Country Link
AU (1) AU2019100336A4 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111272290A (en) * 2020-03-13 2020-06-12 西北工业大学 Temperature measurement thermal infrared imager calibration method and device based on deep neural network
WO2021081597A1 (en) * 2019-10-30 2021-05-06 EarthOffset Holdings Pty Ltd Compost monitoring device and system
CN113591257A (en) * 2021-07-27 2021-11-02 中国水利水电科学研究院 Urban raw water scheduling scheme compiling method for multi-water-source multi-target comprehensive application

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021081597A1 (en) * 2019-10-30 2021-05-06 EarthOffset Holdings Pty Ltd Compost monitoring device and system
CN111272290A (en) * 2020-03-13 2020-06-12 西北工业大学 Temperature measurement thermal infrared imager calibration method and device based on deep neural network
CN111272290B (en) * 2020-03-13 2022-07-19 西北工业大学 Temperature measurement thermal infrared imager calibration method and device based on deep neural network
CN113591257A (en) * 2021-07-27 2021-11-02 中国水利水电科学研究院 Urban raw water scheduling scheme compiling method for multi-water-source multi-target comprehensive application
CN113591257B (en) * 2021-07-27 2022-04-08 中国水利水电科学研究院 Urban raw water scheduling scheme compiling method for multi-water-source multi-target comprehensive application

Similar Documents

Publication Publication Date Title
AU2019100336A4 (en) A method for on-line detection of nitrogen, phosphorous and potassium in compost during bio-digestive process
Qu et al. LAINet–A wireless sensor network for coniferous forest leaf area index measurement: Design, algorithm and validation
Chen et al. Estimating aboveground biomass of grassland having a high canopy cover: an exploratory analysis of in situ hyperspectral data
Agam et al. Application of the Priestley–Taylor approach in a two-source surface energy balance model
Chen et al. Monitoring soil organic carbon in alpine soils using in situ vis‐NIR spectroscopy and a multilayer perceptron
Xu et al. Improving predictions of water and heat fluxes by assimilating MODIS land surface temperature products into the common land model
Imam et al. Design issues for wireless sensor networks and smart humidity sensors for precision agriculture: A review
AU2020101377A4 (en) A process and device for on-line detection of chemical oxygen demand (cod) and biological oxygen demand (bod) in water
Xiong et al. Estimation of evapotranspiration using remotely sensed land surface temperature and the revised three-temperature model
Botha et al. Non-destructive estimation of wheat leaf chlorophyll content from hyperspectral measurements through analytical model inversion
Zhang et al. Estimating wheat yield by integrating the WheatGrow and PROSAIL models
CN106815643A (en) Infrared spectrum Model Transfer method based on random forest transfer learning
Pujahari et al. Intelligent farming system through weather forecast support and crop production
Nassar et al. Assessing daily evapotranspiration methodologies from one-time-of-day sUAS and EC information in the GRAPEX project
Molina-Martínez et al. RaGPS: A software application for determining extraterrestrial radiation in mobile devices with GPS
Cheng et al. Evaluation of UAV-based drought indices for crop water conditions monitoring: A case study of summer maize
Ramzan et al. Internet of trees (IoTr) implemented by highly dispersive electromagnetic sensors
Ren et al. Estimation of litter mass in nongrowing seasons in arid grasslands using MODIS satellite data
Wang et al. Application of hyperspectral technology combined with bat algorithm-AdaBoost model in field soil nutrient prediction
Zhang et al. An improved light use efficiency model by considering canopy nitrogen concentrations and multiple environmental factors
Zhou et al. Development and performance tests of an on-the-go detector of soil total nitrogen concentration based on near-infrared spectroscopy
Chen et al. Validation of MISR land surface broadband albedo
Qu et al. MLAOS: A multi-point linear array of optical sensors for coniferous foliage clumping index measurement
González et al. A low-cost IoT architecture based on LPWAN and MQTT for monitoring water resources in andean wetlands
Tomar et al. Artificial neural network based computational model for the prediction of direct solar radiation in Indian zone

Legal Events

Date Code Title Description
FGI Letters patent sealed or granted (innovation patent)