WO2022245312A1 - A method for estimating soil moisture and a system operating according to said method - Google Patents

A method for estimating soil moisture and a system operating according to said method Download PDF

Info

Publication number
WO2022245312A1
WO2022245312A1 PCT/TR2021/051290 TR2021051290W WO2022245312A1 WO 2022245312 A1 WO2022245312 A1 WO 2022245312A1 TR 2021051290 W TR2021051290 W TR 2021051290W WO 2022245312 A1 WO2022245312 A1 WO 2022245312A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
soil
soil moisture
moisture
users
Prior art date
Application number
PCT/TR2021/051290
Other languages
French (fr)
Inventor
Gülşen Bedia OTÇU
Original Assignee
Hi̇t Bi̇li̇şi̇m Danişmanlik Turi̇zm Hi̇zmetleri̇ Sanayi̇ Ve Ti̇caret Li̇mi̇ted Şi̇rketi̇
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
Priority claimed from TR2021/008288 external-priority patent/TR2021008288A1/en
Application filed by Hi̇t Bi̇li̇şi̇m Danişmanlik Turi̇zm Hi̇zmetleri̇ Sanayi̇ Ve Ti̇caret Li̇mi̇ted Şi̇rketi̇ filed Critical Hi̇t Bi̇li̇şi̇m Danişmanlik Turi̇zm Hi̇zmetleri̇ Sanayi̇ Ve Ti̇caret Li̇mi̇ted Şi̇rketi̇
Publication of WO2022245312A1 publication Critical patent/WO2022245312A1/en

Links

Classifications

    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G7/00—Botany in general
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G25/00—Watering gardens, fields, sports grounds or the like
    • A01G25/16—Control of watering
    • A01G25/167—Control by humidity of the soil itself or of devices simulating soil or of the atmosphere; Soil humidity sensors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Definitions

  • the invention relates to a method for estimating soil moisture and/or guiding users to consume less water and/or informing users of protecting plant health, and to a system operating according to said method.
  • Soil moisture is one of the main factors which influences the soil nutrients. At a low level of precipitations, soil moisture reserve should be considered when selecting the fertilizer ratios. As the soil moisture availability decreases, the normal function and growth of plants is impaired, and the crop yield decreases. As our climate changes, the moisture availability becomes more variable. Soil nutrients and hence, the fertilizer ratios are also affected. In the state of the art, continuous periodic irrigations for places, such as golf courses, green areas, greenhouses and gardens, etc. substantially increase the soil moisture. Thus, substantial damages to the crops occur. Therefore, the soil quality is deteriorated. The main part of the data in the state of the art is the soil moisture data obtained from about 6.500 soil sensors across Europe between 2017 and 2019.
  • Another effective variable is the weather forecast which substantially affect the soil moisture, i.e. , the weather conditions that form the model behavior.
  • a further effective variable is the data of soil type indicating the moisture relations and the effect thereof on the hydrogeological profile of the soil. Serious errors occur in said all data processing results.
  • the object of the invention is to achieve a method for estimating soil moisture and/or guiding users to consume less water and/or informing users of protecting plant health, and a system operating according to said method.
  • Another object of the invention is to model and estimate the soil moisture based on the soil properties and/or weather conditions and/or the other parameters.
  • a further object of the invention is to optimize the irrigation and to estimate the soil moisture depending on the location and location conditions in order to both reduce the excessive costs and to increase the use of intelligent resource.
  • Another object of the invention is to demonstrate the feasibility in terms of technology, application scenarios, user and market uptake potential and scalability.
  • the system of the invention may be used as a infrastructure in a wide range of application areas, from personal landscapes (gardens) to greenhouses, from fields to golf courses and all green areas.
  • the invention may improve the model estimation performance and iteratively improve itself by using more datasets. It produces estimations for both obtaining an insight about the soil moisture, irrigation frequency, irrigation amount and informing the users of heavy weather conditions, irrigation requirements, or water level anomalies. Furthermore, its unique feature is caused by the deep learning algorithms in the core thereof, while it offers a resource- efficient, cost-effective and easy-to-use solution.
  • the invention has been developed, trained and tested with a soil control sensor dataset, a DarkSky weather forecast dataset and a dataset indicating the soil type humidity capacity which represents the top soil easily available water capacity, called EAWC.
  • a daily (a period of 24 hours) estimation may be carried out due to the LSTM (Long Short Term Memory) deep learning model of “high accuracy”, the MAPE (Median absolute percentage error) score of which is 6.9%.
  • a weekly estimation may also be carried out.
  • the invention estimates the soil moisture and anomalies using a deep learning model, called LSTM (Long Short Term Memory). Estimations are based on the data measured 5 using soil sensors and hourly weather forecast for the sensor positions. Furthermore, the soil types obtained using ESDAC (European Soil Database Center) and the hydrogeological units are used as a feature.
  • LSTM Long Short Term Memory
  • the invention may estimate the moisture status from the soil moisture in a micro green 10 field to the another locations having the same/similar features at a different place in the world with a high accuracy.
  • the system offers a capacity to make different applications and to create maximum impact and value. It will generate a decision supporting mechanism and a smart 15 infrastructure for developing new solutions due to the dynamic learning structure thereof.
  • Figure 1 is a schematic block diagram of the system according to the invention.
  • Figure 2 is a diagram of the working principle of the system according to the invention.
  • Figure 3 is an overall flow chart of the method according to the invention.
  • Figure 4 is a view of an exemplary application of the sensors collecting the soil moisture data.
  • Figure 5 is a view of soil moisture changes based on the soil sensor data.
  • Figure 6 is a view of the real values and estimated values of the soil moisture.
  • test set data known standard data
  • training set data data created as a result of machine learning
  • the system (100) of the invention comprises at least one device (1) which allows a user to access the system (100) and at least one server (2) in which the data analyses are performed using artificial intelligence algorithms.
  • the device (1) comprises at least one interface (1.1) which allows a user to obtain data about soil moisture and/or irrigation frequency and/or irrigation amount and to access information on heavy weather conditions and/or irrigation requirements and/or water level anomalies, at least a first control unit (1.2) which processes the requests from a user and actuates the interface (1.1), at least a first storage unit (1.3) which stores said interface (1.1) on the device (1) and stores the data from the server (2), and at least a first communication unit (1.4) which provides communication between the device (1) and the server (2).
  • interface (1.1) which allows a user to obtain data about soil moisture and/or irrigation frequency and/or irrigation amount and to access information on heavy weather conditions and/or irrigation requirements and/or water level anomalies
  • at least a first control unit (1.2) which processes the requests from a user and actuates the interface (1.1)
  • at least a first storage unit (1.3) which stores said interface (1.1) on the device (1) and stores the data from the server (2)
  • at least a first communication unit (1.4) which provides
  • the device (1) comprises at least one screen (not shown and enumerated in the drawings).
  • the interface (1.1) is accessed via said screen.
  • the server (20) comprises at least a second control unit (2.1) which performs data analysis to achieve deep learning (LSTM) (Long Short Term Memory) and processes/controls any data related to the system (100), at least a second storage unit (2.2) comprising at least one database (2.2.1) in which the data obtained from the users are present, and at least a second communication unit (2.3) which provides communication with the device (1).
  • LSTM deep learning
  • 2.3 second communication unit
  • the coding language of the interface (1.1) is Python. Flask library is used for programming the interface (1.1). However, it should not be considered as limited thereto in practice.
  • LSTM Long Short Term Memory
  • Machine inputs • A soil control sensor dataset, a DarkSky weather forecast dataset and a dataset indicating the soil type humidity capacity which represents the top soil easily available water called EAWC.
  • Machine outputs C
  • Said machine outputs ( ) may be transferred via a Ul (user interface) and may be integrated into the irrigation systems (smart irrigation) and/or mobile applications/current systems using an API (application programming interface).
  • the system (100) of the invention operates according to the following method (200) steps. - Collecting (201) data in a database (2.2.1), such as weather forecast data and/or soil control sensor data and/or soil type moisture capacity data Subjecting (202) data to data cleaning and normalization procecesses by the second control unit (2.1)
  • step 201 a soil control sensor dataset, a DarkSky weather forecast dataset in which information on backward-looking hourly weather forecast is present and a dataset indicating the soil type humidity capacity which represents the top soil easily available water called EAWC are used.
  • EAWC soil moisture type
  • LSTM Long Short Term Memory
  • Figure 4 shows a view of an exemplary application of the sensors collecting the soil moisture data. It represents a data chunk between March, 2019 and August, 2019.
  • the first point marked in Figure 4 of the sensors collecting the soil moisture data represents the beginning of a data chunk.
  • the second point marked represents the end of a data chunk.
  • the marking is continued in this way at certain intervals.
  • the rightmost image formed by the marked points depicts a single part of the sensor.
  • Figure 5 is a view of a soil moisture change based on the soil sensor data. It represents the soil moisture change between May, 2019 and June, 2019.
  • the soil moisture type (EAWC) dataset to be used is converted to an appropriate format.
  • the dataset comprises data X,Y and the points which forms a polygon.
  • As the polygonal data have point data, only latitude and longitude data are used for mapping to the closest sensor point.
  • Figure 6 is a view of the real values and estimated values of the soil moisture. Processes for soil moisture were performed between August 4, 2019 and Augist 14, 2019.
  • the letter “a” indicates a real value
  • the letter “x” indicates the estimated value
  • the symbol “+” indicates the changes within 24 hours.
  • the invention relates to a method (200) for estimating soil moisture and/or guiding users to consume less water and/or informing users of protecting plant health, and to a system (100) operating according to said method (200), and is applicable to the industry.

Abstract

The invention relates to a method (200) for estimating soil moisture and/or guiding users to consume less water and/or informing users of protecting plant health, and to a system (100) operating according to said method (200).

Description

A METHOD FOR ESTIMATING SOIL MOISTURE AND A SYSTEM OPERATING
ACCORDING TO SAID METHOD Technical Field
The invention relates to a method for estimating soil moisture and/or guiding users to consume less water and/or informing users of protecting plant health, and to a system operating according to said method.
Prior Art
Soil moisture is one of the main factors which influences the soil nutrients. At a low level of precipitations, soil moisture reserve should be considered when selecting the fertilizer ratios. As the soil moisture availability decreases, the normal function and growth of plants is impaired, and the crop yield decreases. As our climate changes, the moisture availability becomes more variable. Soil nutrients and hence, the fertilizer ratios are also affected. In the state of the art, continuous periodic irrigations for places, such as golf courses, green areas, greenhouses and gardens, etc. substantially increase the soil moisture. Thus, substantial damages to the crops occur. Therefore, the soil quality is deteriorated. The main part of the data in the state of the art is the soil moisture data obtained from about 6.500 soil sensors across Europe between 2017 and 2019. Another effective variable is the weather forecast which substantially affect the soil moisture, i.e. , the weather conditions that form the model behavior. A further effective variable is the data of soil type indicating the moisture relations and the effect thereof on the hydrogeological profile of the soil. Serious errors occur in said all data processing results.
There is a need for developing systems which do not exist in the state of the art and eliminate the above mentioned disadvantages. Brief Description of the Invention
The object of the invention is to achieve a method for estimating soil moisture and/or guiding users to consume less water and/or informing users of protecting plant health, and a system operating according to said method.
Another object of the invention is to model and estimate the soil moisture based on the soil properties and/or weather conditions and/or the other parameters. A further object of the invention is to optimize the irrigation and to estimate the soil moisture depending on the location and location conditions in order to both reduce the excessive costs and to increase the use of intelligent resource.
Another object of the invention is to demonstrate the feasibility in terms of technology, application scenarios, user and market uptake potential and scalability.
The system of the invention may be used as a infrastructure in a wide range of application areas, from personal landscapes (gardens) to greenhouses, from fields to golf courses and all green areas.
On the other hand, as the invention has a dynamic learning capacity, it may improve the model estimation performance and iteratively improve itself by using more datasets. It produces estimations for both obtaining an insight about the soil moisture, irrigation frequency, irrigation amount and informing the users of heavy weather conditions, irrigation requirements, or water level anomalies. Furthermore, its unique feature is caused by the deep learning algorithms in the core thereof, while it offers a resource- efficient, cost-effective and easy-to-use solution.
On the other hand, it provides a large amount of data and allows to obtain significant results in said data and to convert the interpretations to the estimations of high accuracy.
The advantages of the system are as follows.
It optimizes the irrigation duration.
It obtains data from the multi-dimensional datasets (sensor, soil, weather forecast data) It has a capacity to have better performance by improving LSTM model and learning iteratively.
It provides estimations of high accuracy.
It is an extendable and scalable system so as to be an infrastructure for multiuse.
It monitors the soil moisture.
It helps to save water by estimating the amount of water.
It struggles with the climate change and the social challenges related to the sustainable development goals.
The invention has been developed, trained and tested with a soil control sensor dataset, a DarkSky weather forecast dataset and a dataset indicating the soil type humidity capacity which represents the top soil easily available water capacity, called EAWC. A daily (a period of 24 hours) estimation may be carried out due to the LSTM (Long Short Term Memory) deep learning model of “high accuracy”, the MAPE (Median absolute percentage error) score of which is 6.9%. A weekly estimation may also be carried out.
The actions and methods applied to develop the system are provided in Table-1.
Table-1. The actions and methods applied to develop the system
Figure imgf000005_0001
Figure imgf000005_0002
M
E
T
H
O
D
Figure imgf000006_0001
The invention estimates the soil moisture and anomalies using a deep learning model, called LSTM (Long Short Term Memory). Estimations are based on the data measured 5 using soil sensors and hourly weather forecast for the sensor positions. Furthermore, the soil types obtained using ESDAC (European Soil Database Center) and the hydrogeological units are used as a feature.
The invention may estimate the moisture status from the soil moisture in a micro green 10 field to the another locations having the same/similar features at a different place in the world with a high accuracy.
The system offers a capacity to make different applications and to create maximum impact and value. It will generate a decision supporting mechanism and a smart 15 infrastructure for developing new solutions due to the dynamic learning structure thereof.
Description of the Invention
20 Figure 1 is a schematic block diagram of the system according to the invention.
Figure 2 is a diagram of the working principle of the system according to the invention. Figure 3 is an overall flow chart of the method according to the invention.
Figure 4 is a view of an exemplary application of the sensors collecting the soil moisture data. Figure 5 is a view of soil moisture changes based on the soil sensor data. Figure 6 is a view of the real values and estimated values of the soil moisture.
Description of the References in the Drawings
The numbers in the drawings are provided below in order to provide a better understanding of the invention:
100. System
1. Device
1.1 Interface
1.2 First control unit
1.3 First storage unit
1.4 First communication unit
2. Server
2.1 Second control unit
2.2 Second storage unit 2.2.1 Database
2.3 Second communication unit G - Machine input
Q - Machine output
200. Method
201. Collecting data in a database (2.2.1), such as weather forecast data and/or soil control sensor data and/or soil type moisture capacity data
202. Subjecting data to data cleaning and normalization processes by the second control unit (2.1)
203. Discretizing data as a test set data (known standard data) and/or a training set data (data created as a result of machine learning)
204. Modelling the data discretized as a training set data
205. Modelling the data discretized as a test set data
206. Estimating the outputs using the machine and test input set, the learning processes of which are completed
Detailed Description of the Invention The system (100) of the invention comprises at least one device (1) which allows a user to access the system (100) and at least one server (2) in which the data analyses are performed using artificial intelligence algorithms.
The device (1) comprises at least one interface (1.1) which allows a user to obtain data about soil moisture and/or irrigation frequency and/or irrigation amount and to access information on heavy weather conditions and/or irrigation requirements and/or water level anomalies, at least a first control unit (1.2) which processes the requests from a user and actuates the interface (1.1), at least a first storage unit (1.3) which stores said interface (1.1) on the device (1) and stores the data from the server (2), and at least a first communication unit (1.4) which provides communication between the device (1) and the server (2).
In a preferred embodiment of the invention, the device (1) comprises at least one screen (not shown and enumerated in the drawings). The interface (1.1) is accessed via said screen.
The server (20) comprises at least a second control unit (2.1) which performs data analysis to achieve deep learning (LSTM) (Long Short Term Memory) and processes/controls any data related to the system (100), at least a second storage unit (2.2) comprising at least one database (2.2.1) in which the data obtained from the users are present, and at least a second communication unit (2.3) which provides communication with the device (1).
In a preferred embodiment of the invention, the coding language of the interface (1.1) is Python. Flask library is used for programming the interface (1.1). However, it should not be considered as limited thereto in practice.
On the other hand, LSTM (Long Short Term Memory) is designed in an open manner so as to avoid a long-term dependency problem, and such algorithms have a capacity to remind the information for a long time rather making an effort to re-learn.
Machine inputs (G) • A soil control sensor dataset, a DarkSky weather forecast dataset and a dataset indicating the soil type humidity capacity which represents the top soil easily available water called EAWC. Machine outputs (C)
• Allowing a user to obtain data about soil moisture and/or irrigation frequency and/or irrigation amount and to access information on heavy weather conditions and/or irrigation requirements and/or water level anomalies Said machine outputs ( ) may be transferred via a Ul (user interface) and may be integrated into the irrigation systems (smart irrigation) and/or mobile applications/current systems using an API (application programming interface).
The system (100) of the invention operates according to the following method (200) steps. - Collecting (201) data in a database (2.2.1), such as weather forecast data and/or soil control sensor data and/or soil type moisture capacity data Subjecting (202) data to data cleaning and normalization procecesses by the second control unit (2.1)
Discretizing (203) data as a test set data (known standard data) and/or a training set data (data created as a result of machine learning)
Modelling (204) the data discretized as a training set data Modelling (205) the data discretized as a test set data
Estimating (206) the outputs using the machine and test input set, the learning processes of which are completed,
In step 201, a soil control sensor dataset, a DarkSky weather forecast dataset in which information on backward-looking hourly weather forecast is present and a dataset indicating the soil type humidity capacity which represents the top soil easily available water called EAWC are used. In addition, both in the soil control sensor dataset and the weather forecast set, parameters such as time measurement, positional values and data chunks and parameters such as positional mapping, distance calculation and dataset merging for the soil moisture type (EAWC) are calculated. In step 202, the sensors collecting the soil moisture data operate by queuing the hourly data at certain intervals, thereby preventing the processing of the missing data. Thus, the algorithm is prevented from producing poor results.
In steps 204 and 205, LSTM (Long Short Term Memory) modelling method among machine learning methods is used.
Figure 4 shows a view of an exemplary application of the sensors collecting the soil moisture data. It represents a data chunk between March, 2019 and August, 2019.
The first point marked in Figure 4 of the sensors collecting the soil moisture data represents the beginning of a data chunk. The second point marked represents the end of a data chunk. The marking is continued in this way at certain intervals. The rightmost image formed by the marked points depicts a single part of the sensor.
Figure 5 is a view of a soil moisture change based on the soil sensor data. It represents the soil moisture change between May, 2019 and June, 2019.
It has been observed in Figure 5 that there is an uninterrupted and accurate sensor data flow between May 20, 2019 and June 17, 2019 through the current and healthy sensor data obtained in Figure 4. The data outside the mentioned date range have been observed to be incorrect data.
The soil moisture type (EAWC) dataset to be used is converted to an appropriate format. The dataset comprises data X,Y and the points which forms a polygon. As the polygonal data have point data, only latitude and longitude data are used for mapping to the closest sensor point.
The results of the training set and test set obtained using position data, data chunks, hour information, etc. are provided in Table-2 below. Tabie-2. Results of training set and test set
Figure imgf000011_0001
Figure 6 is a view of the real values and estimated values of the soil moisture. Processes for soil moisture were performed between August 4, 2019 and Augist 14, 2019. In Figure 6, the letter “a” indicates a real value, the letter “x” indicates the estimated value, and the symbol “+” indicates the changes within 24 hours.
Industrial Applicability of the Invention The invention relates to a method (200) for estimating soil moisture and/or guiding users to consume less water and/or informing users of protecting plant health, and to a system (100) operating according to said method (200), and is applicable to the industry.
The invention is not limited to the above descriptions, and a person skilled in the art can easily reveal the different embodiments of the invention. These should be considered within the scope of protection of the invention claimed in the claims.

Claims

1. A system (100) for estimating soil moisture and/or guiding users to consume less water and/or informing users of protecting plant health, comprising: at least one device (1) which allows at least one user to access the system (100), and at least one server (2) in which the data analyses are performed using artificial intelligence algorithms, characterized by at least one device (1) comprising at least one interface (1.1) which allows a user to obtain data about soil moisture and/or irrigation frequency and/or irrigation amount and to access information on heavy weather conditions and/or irrigation requirements and/or water level anomalies, at least a first control unit (1.2) which processes the requests from a user and actuates the interface (1.1), at least a first storage unit (1.3) which stores said interface (1.1) on the device (1) and stores the data from the server (2), and at least a first communication unit (1.4) which provides communication with the server (2); and at least one server (2) comprising at least a second control unit (2.1) which performs data analysis to achieve deep learning (LSTM) (Long Short Term Memory) and processes/controls any data related to the system (100), at least a second storage unit (2.2) comprising at least one database (2.2.1) in which the data obtained from the users are present, and at least a second communication unit (2.3) which provides communication with the device (1).
2. A method (200) for estimating soil moisture and/or guiding users to consume less water and/or informing users of protecting plant health, characterized in that it comprises the following steps:
Collecting (201) data in a database (2.2.1), such as weather forecast data and/or soil control sensor data and/or soil type moisture capacity data Subjecting (202) data to data cleaning and normalization procecesses by the second control unit (2.1)
Discretizing (203) data as a test set data (known standard data) and/or a training set data (data created as a result of machine learning)
Modelling (204) the data discretized as a training set data Modelling (205) the data discretized as a test set data Estimating (206) the outputs using the machine and test input set, the learning processes of which are completed.
3. A method (200) as claimed in claim 2, characterized by parameters in step 201, such as use of a soil control sensor data set, a DarkSky weather forecast data set in which information on backward-looking hourly weather forecast is present and a dataset indicating the soil type moisture capacity which represents the top soil easily available water capacity, called EAWC; parameters such as time measurement, positional values and data chunks in the soil control sensor data set and weather forecast set for the soil moisture type (EAWC); and parameters such as positional mapping, distance calculation and dataset merging.
4. A method (200) as claimed in claim 3, characterized in that in step 202, the sensors collecting the soil moisture data operate by queuing the hourly data at certain intervals, thereby preventing the processing of the missing data.
5. A method (200) as claimed in claim 4, characterized in that in steps 204 and 205, LSTM (Long Short Term Memory) modelling among the machine learning methods is used.
PCT/TR2021/051290 2021-05-18 2021-11-25 A method for estimating soil moisture and a system operating according to said method WO2022245312A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
TR2021008288 2021-05-18
TR2021/008288 TR2021008288A1 (en) 2021-05-18 A METHOD TO ESTIMATE SOIL MOISTURE AND A SYSTEM THAT WORKS ACCORDING TO THE METHOD IN SAID

Publications (1)

Publication Number Publication Date
WO2022245312A1 true WO2022245312A1 (en) 2022-11-24

Family

ID=84141583

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/TR2021/051290 WO2022245312A1 (en) 2021-05-18 2021-11-25 A method for estimating soil moisture and a system operating according to said method

Country Status (1)

Country Link
WO (1) WO2022245312A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109937856A (en) * 2019-04-03 2019-06-28 北京邮电大学 Household grass xylophyta automatic irrigation system and its working method
CN110084367A (en) * 2019-04-19 2019-08-02 安徽农业大学 A kind of Forecast of Soil Moisture Content method based on LSTM deep learning model
CN111561972A (en) * 2020-06-18 2020-08-21 华南农业大学 Soil water content prediction system and method based on time sequence

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109937856A (en) * 2019-04-03 2019-06-28 北京邮电大学 Household grass xylophyta automatic irrigation system and its working method
CN110084367A (en) * 2019-04-19 2019-08-02 安徽农业大学 A kind of Forecast of Soil Moisture Content method based on LSTM deep learning model
CN111561972A (en) * 2020-06-18 2020-08-21 华南农业大学 Soil water content prediction system and method based on time sequence

Similar Documents

Publication Publication Date Title
Luo et al. A comparison of spatial interpolation methods to estimate continuous wind speed surfaces using irregularly distributed data from England and Wales
Burrough Development of intelligent geographical information systems
US20160003792A1 (en) Functional soil maps
EP2916647A1 (en) A method and system for automated differential irrigation
CN110596008B (en) Plot-based soil nutrient digital mapping method for agricultural region of Chinese Hongsheng plain
CN105120433A (en) WLAN indoor positioning method based on continuous sampling and fuzzy clustering
CN106600037B (en) Multi-parameter auxiliary load prediction method based on principal component analysis
Butler et al. Extreme value analysis of decadal variations in storm surge elevations
CN113344291A (en) Urban inland inundation range forecasting method, device, medium and equipment
CN112585505A (en) Determining location-specific weather information for agronomic decision support
CA3114428A1 (en) Method and system of real-time simulation and forecasting in a fully-integrated hydrologic environment
Requena et al. Flood frequency analysis at ungauged sites based on regionally estimated streamflows
JP2015010927A (en) Observation value processing device, observation value processing method, and observation value processing program
Reinhardt et al. Comparison of different wind data interpolation methods for a region with complex terrain in Central Asia
WO2022245312A1 (en) A method for estimating soil moisture and a system operating according to said method
Boyko et al. Post-processing climate projections of precipitation for the Po river basin: will Italy's North become water-constrained?
CN116304391A (en) Method and system for generating recommended selection area after map area frame selection
CN115016036A (en) Agricultural weather monitoring method, device, equipment and storage medium
CN109636018A (en) Calculate the method and device of temperature and the distant correlativity of climatic factor
CN111667112B (en) Fishery resource abundance gray prediction model optimization method and application thereof
CN108712317A (en) A kind of Urban population space-time dynamic cognitive method and system based on mobile social networking
CN113902160A (en) Water regulation method applied to hydro-junction engineering
CN109299521B (en) Method and device for determining runoff total control rate
Bai et al. Influence of varied drought types on soil conservation service within the framework of climate change: insights from the Jinghe River Basin, China
Nandi et al. Geographical Information System (GIS) in water resources engineering

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21940974

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE