EP4081959A1

EP4081959A1 - Agricultural decision support system

Info

Publication number: EP4081959A1
Application number: EP20906140.7A
Authority: EP
Inventors: Sinan OZ; Yusuf KURUCU; Emre TUNALI; Osman BAYTAROGLU
Original assignee: Agrovisio Oue
Current assignee: Agrovisio Oue
Priority date: 2019-12-26
Filing date: 2020-12-02
Publication date: 2022-11-02
Also published as: EP4081959A4; WO2021133310A1

Abstract

The invention relates to an agricultural decision support system that classifies agricultural products and monitors the phenological development of the products by analysing multispectral satellite images with the help of machine learning and remote sensing techniques.

Description

Agricultural Decision Support System Technical Field

The invention relates to an agricultural decision support system that classifies agricultural products and monitors the phenological development of the products by analysing multispectral satellite images with the help of machine learning and remote sensing techniques. Prior Art

Climate change, population growth and depletion of natural resources, especially water; threatens sustainable food production and security. This situation rapidly increases the importance and priority of food production and security. While the world population is expected to increase by more than 35% in the next 35 years, it is necessary to increase agricultural production by 100% to supply sufficient food. It is thought that the developing countries like Turkey will be most affected by the increase in demand [l](Figure 1). Figure 1 shows the graph of the daily calorie consumption over the years. In order to adapt to this process, it becomes a necessity to produce effective and dynamic agricultural policies (support, incentives, etc.) and to make ground truth controls. For this, detailed, accurate and uninterrupted data production is required.

There are few existing solutions operating domestically in the agricultural remote sensing and analysis sector. Remote sensing solutions are provided by Nik Sistem under the title of consultancy. Analyses made by Nik Sistem are not real-time, however they use the NDVI analyses, which use the visible band and infrared light wavelengths of the spectrum, with object-based classification methods. The Nik System cannot obtain numerical data on efficiency, yield, product identification and classification, and damage impact; and cannot follow soil feature-based change.

UHUZAM, operating under ITU, is an application and research centre. In this centre, within the scope of the Agricultural Monitoring and Information System (TARBiL) project, periodic monitoring of the cultivated areas with high spatial resolution satellite images during the phenological period, determination of product types and spatial distribution by object-based image classification, production of plant indexes for tracking product development, transferring these images, classification and plant index data produced and statistical result reports to the relevant units under the Ministry of Food, Agriculture and Livestock are executed.. The methods applied in the centre have not been converted into service, and the works carried out within the scope of the TARBIL project since 2008 have been brought to TRL 3 level, but beyond this level they have not been converted into ready-to-use models.

Precision agricultural practices are developed by analysing agricultural areas with images taken from satellite and air platforms within Tiibitak UZAY. The products grown in the GAP region are analysed by using data from air platforms with multi band satellite images, including RASAT and Gokturk-2 images. As a result of the analyses, it is aimed to determine the crops sown in agricultural land, estimate the crop, the fertilizer and irrigation need of the soil, and the plant disease status. At this point, product tracking is done with the NDVI technique and the reflection values are recorded through this technique.

Study US20050234691A1 emphasizes that NDVI analysis is not sufficient to monitor crop development and estimate the yield. For this reason, NDVI has turned to the use of physical data such as soil moisture, rainfall, and surface temperature. In our proposed invention, a plot study will be carried out to estimate the yield by obtaining more data by increasing our analyses made for the solution of the same problem above NDVI at the highest rate from satellite images.

Purpose of the Invention

The present invention relates to an agricultural decision support system that meets the above-mentioned requirements, eliminates all disadvantages, and brings some additional advantages.

The primary purpose of the invention is to contribute to the production of quality and efficient food by using the resources correctly and on time; to provide solutions that will secure economic and sustainable agricultural production.

In its simplest form, the invention can be expressed as an agricultural decision support system that follows the phenological development of agricultural products by analysing multispectral satellite images with the help of machine learning and remote sensing techniques. In realizing the invention, generalization of reflection models, tracking of the reflection values of the plant using all wavelengths offered by satellites and product classification with spectral product signatures are the most basic steps. For this purpose, using all bands (wavelengths) in satellite images will be a critical threshold for perceiving the soil in which the plant grows and thus determining the development level of the plant, as well as allowing a better understanding of the plant. Thanks to the features obtained in this way; automatic recognition of agricultural products, automatic classification, automatic detection of the fertility value of the soil and determination of the yield by using this perceived value and the level of development obtained by using reflection values and product spectral signatures can be realized through the system described in the invention.

By making use of new technologies such as big data analysis, computer vision and deep learning methods with the invention in question; it is ensured that various strategic products are automatically and precisely identified, mapped and developed by looking at satellite images. By presenting standardized, systematic, and scalable analyses and insights for the needs of the agricultural sector with the invention; a product can be created that contributes to progress in predictability and plannability in agriculture and supports data-based agricultural production.

In the system subject to invention, agricultural knowledge and machine learning areas of expertise are combined with an interdisciplinary study, so that large data analysis can be performed from field scale to national scale based on soil characteristics and real-time satellite images.

With the analysis platform described in the invention, the obtained information can be segmented, and product identification can be made in parcel and sub-parcel detail, products can be separated according to their development level and efficiency, yield estimation can be made, and anomalies and damages in product development can be detected.

Analyses mentioned in the invention can be carried out using computer vision techniques with a resolution below the plot scale. Thus, in cases where agricultural parcels are not used for agricultural purposes or have more than one product pattern in a parcel, the accuracy of the cultivated area, yield estimation is increased. The same technical ability also improves the performance in terms of the location of the damaged area estimated by the damage detection module and the clarity of the area.

With the invention, it is aimed to manage the analysis data of the risks in agricultural production and use it as a strategy formulation and decision support system in agricultural production, thus contributing to planning, predictable and sustainable agricultural production. The components that make up the invention, the System General Flow Chart, are shown in Figure 2.

With the invention, it is shown as the superiority of the accuracy and sensitivity of the plant indexes obtained based on the multispectral product signature over object- oriented indexes. With the invention, a multispectral product signature is created, and in all subsequent analyses, remote sensing techniques are enriched with machine learning techniques. The invention is more precise and detailed than the systems in the prior art in terms of both product identification and analysis methods.

The feature calculation technique used in classification is a new method. This method examines the effects of reflections at different wavelengths that make up the satellite images in relation to each other throughout the phenological phase. In this way, the acquired features become more distinctive and generalizable than the indexes currently in use. In addition, the segmentation and normalization existing in our solution provides a spatial resolution that can be exceeded by parcel resolution.

In field level crop development tracking, instead of NDVI solutions made with two bands, utilizing all bands of the satellite increases sensitivity. Notifying the farmer of crop development and problematic sections in the field will allow interventions and increase productivity. Unlike equivalent products that make analyses for agricultural data production, in addition to focusing on big data and advancing by making machine learning, our solutions are shaped by soil knowledge in agricultural engineering level. The analyses and field studies required for the use of soil information have been carried out in our company and have been produced in the form of a map that can be used for years. By using the advantage of interdisciplinary work, the yield can be estimated by the farmer by combining soil information with multi-band crop development follow-up results. Thus, the product supply quantity data will be known correctly, and the price policy will be more successful. Reflecting this to the country scale may help to make more concrete decisions in pricing in agricultural exchanges. With the development and yield tracking, the producer will be able to estimate the harvest amount, sell his product at a fair price and find affordable financial support.

The invention is based on the ideas of making decisions on current data using every new satellite image and automating agricultural processes. For this reason, the output formats are designed to be compatible with agricultural information systems in accordance with the general GIS formats and can be opened and examined in other commercial platforms (.shp, .dbf, .tif etc.). Since our solution does not require costly exploration methods such as infrastructure installation in production areas or using drones, it can be scaled quickly and used automatedly in large areas. In this way, it will be an infrastructure that can help decision makers to see the whole with the analysis of the big data produced.

In a preferred embodiment of the invention, the method used in the system subject to invention makes decisions based on up-to-date data by using each new satellite image and automates agricultural processes. In another preferred embodiment of the invention, the stage of creating digital signatures of the product developments mentioned in the method includes creating a histogram from the pixel reflection values taken from each band of satellite images that coincide with the relevant parcels for the specified products, creating the probability density function (pdf) that gives the distribution probabilities of the pixel values for the relevant band (imaging wavelength) of the relevant satellite image of the product by normalizing the histogram with the total number of pixels, recording these probability density functions as temporal series by repeating in all bands (wavelengths) of each new satellite image throughout the phenological phase for different samples, creating multidimensional features on which plant growth is modelled, producing probability maps containing the expected reflection values of the specific product in a particular region throughout the year, as a result of this process repeated with each reference parcel obtained from the training data set, creating digital signatures of product developments by repeating this process for different products and different regions. In another preferred embodiment of the invention, it is an electronic device using the mentioned method. Electronic devices using the method are in the form of computers, smart phones, tablets, smart devices and all devices that can connect to the internet, etc.

In another preferred embodiment of the invention, the product classification mentioned in the method is made by examining the effects of reflections of different wavelengths that form satellite images based on the matched features throughout the phenological phase in relation to each other.

In another preferred embodiment of the invention, by comparing the declaration control mentioned in the method with the farmer's declaration obtained by various methods (farmer registration systems, third party database containing the product declaration for insurance/credit/premium etc.) it is done by giving a warning to the operator via the information platform if the result of agreement with the declaration is negative.

In another preferred embodiment of the invention, the development monitoring mentioned in the method is made by using multispectral reflection values obtained from satellite images by using all bands of the satellite, converting the development values of the products into metrics, and evaluating whether the product follows the expected development process, and using supervised learning techniques.

In another preferred embodiment of the invention, the harvest estimation mentioned in the method is made by finding the damage presence on the planted areas on a parcel basis, determining the amount of damage on an area basis and to report the damage to the user by estimating in tonnage and using product development information and soil characteristics.

In another preferred embodiment of the invention, it makes decisions based on updated data using each new satellite image and automates agricultural processes. In another preferred embodiment of the invention, the data mentioned in the method is stored for each agricultural parcel on a one-year or multi-year basis.

In another preferred embodiment of the invention, it is to present the agricultural decision support suggestions mentioned in the method to the user by visualizing the data according to the user analysis input using the Information platform and by examining the data with one-year and multi-year models created by agricultural experts.

Another preferred embodiment of the invention is a desktop, mobile (Android/ iOS), or web application platform that allows the information platform mentioned in the method to provide inputs to the analysis modules in line with the user authorization and the opportunity to examine their outputs, accessing the outputs of all analysis modules, reporting and visual outputs to be given according to analysis types.

Spectral signature product catalogue, which is one of the main outcomes of the invention and has not yet been produced in Turkey until today, however can be used in many areas of public and private organizations, is a strategic product for the needs.

Description of Figures

In Figure- 1, the graph of the daily calorie consumption increase by years is demonstrated.

In Figure-2, System General Flow Chart is demonstrated.

In Figure-3, System General Flow Chart is demonstrated.

In Figure-4, overlapping the polygons of the parcels with satellite image is demonstrated.

In Figure-5, a sample product development output is demonstrated. In Figure-6, a sample segmentation image is demonstrated.

In Figure-7, each administrative unit is represented with a sub-administrative level unit (country with provinces, province with districts, district with villages, village with parcels) in the sample platform view.

Figure-8 demonstrates the village analysis result produced and visualized by combining sample parcel-based analyses (mosaic).

Figure-9 demonstrates the district analysis result produced and visualized by combining the sample parcel-based analysis (mosaic).

Figure- 10 demonstrates the presentation of the sample parcel-based analysis results as a series of images.

Figure- 11 demonstrates the sample parcel -based analysis and visual and textual information.

Figure- 12 demonstrates a sample analysis and classification result.

Figure- 13 demonstrates the sample reference parcels and management screen.

Explanation of the Invention

In this detailed description, the agricultural decision support system subject to the invention is explained only with examples that will not have any restrictive effect on better understanding of the innovation.

To be able to observe and interpret the target crop pattern from satellite images, it is necessary to know the phenological stages of each plant species. The soil coverage rates vary during the phenological stages of each crop pattern. Accordingly, the numerical values in the bands in which the reflection values of the different wavelengths of light are recorded in satellite images also change. By knowing these values, it is possible to define the product pattern (determine product signatures). Supervised learning techniques, SVM (support vector machines) and decision trees, are used to implement product recognition and development tracking modules. For this, it is necessary to determine the attributes that can represent the products regionally and create development models by training the system with these attributes collected during the phenological stages of different product types. Digital signatures of product developments have been established by training our system among developmental stage and reference agricultural parcels with known types of products, which were collected from throughout Turkey. Thus, using the product development models obtained, product types were trained for their development characteristics.

Registration of parcels and satellite images:

It is the preliminary step of all existing processes. Coordinated polygon information with agricultural parcels is placed on satellite image to determine which pixels are in which parcel. Thus, the analyses required for each parcel can be applied one by one. This process is completed by matching the coordinate information of each satellite image to be examined and the corner coordinates of the polygons of the parcels.

In Figure 4, registration of the polygons of the parcels with satellite image is demonstrated.

Generating digital signatures of product developments:

In the creation of a digital product signature, images taken at certain time intervals are used to follow the product development from the reference parcels that we know which product is being grown. Reference plots, in which the product characteristics of common field crops to be monitored are best represented, are determined by agricultural experts and the locations (coordinates) of these parcels are recorded. These coordinates are followed with up-to-date satellite images, including the planting and harvest times, and the development stages of different products in different regions are learned. Monitoring the product pattern in the parcel from the current satellite images and recording the changes in the reflection values are the basic data of the learning task.

As in all machine learning applications, in this context, the data set is a factor that directly affects learning success. For this reason, there is a need for a high descriptive and large data set as possible. Selecting highly descriptive reference plots for products while creating this data set requires a significant amount of agricultural knowledge and experience. In order to meet this agricultural knowledge and experience, the data set has been shaped by field studies in line with the experiences in studies of our consultant professor and one of the inventors, who has been working on remote product detection for many years, Prof. Dr. Yusuf Kurucu, At the end of the study, a digital signature (reference catalogue) of the product developments at the level of sub-regions and phenological stage of selected field crops was created. Thus, in other words, a model of the usual development phase of the product is created by learning the expected multi-band reflection values during the phenological stages of the specified products.

For the products determined for the creation of digital signatures, a histogram is created from the pixel reflection values taken from each band of satellite images that coincide with the relevant parcels. This histogram is normalized with the total number of pixels and the probability density function (pdf) is created for the relevant band (imaging wavelength) of the relevant satellite image of the product. These probability density functions give the distribution probabilities of pixel values for the relevant band of that product. These probability density functions are repeated in all bands (wavelengths) of each new satellite image throughout the phenological phase for different samples and are recorded as temporal series. Thus, multidimensional features on which plant growth is modelled are formed. As a result of this process, which is repeated with each reference parcel obtained from the training data set, probability maps containing the expected reflectance values of a particular product in a particular region throughout the year are produced. The effect of each reference parcel on the average is considered the same. This process was repeated for different products and different regions, and digital product signatures were completed. The digital signatures obtained were tested with the part of the data labelled and collected as a reference (cross-validation) and the process was completed.

Figure 5 shows a sample product development output. Analysis of Parcels Given as User Input:

Our solution, which is the basis for this application, is an analysis and information platform. Users define the agricultural parcels they want to analyse and the analysis types they want to apply through this interface. Access to analysis results is also made through this interface. The data obtained from analysis modules are presented to the user in visual and textual reports through the same interface. The interface, which enables different types of analysis to be performed through different menus for different user groups, can also present the reports as visual and textual reports customized for the relevant user types. The basis of our analysis is to examine the time-dependent changes of all bands of satellite images belonging to the analysed parcel and their correlations with each other. In other words, as a result of simultaneous reception of the responses of light to different wavelengths in the development process of plants, certain evaluations are made by making comparisons with plant species-specific product signatures on attributes with high generalizability as well as in-class distinctiveness. The analysis modules of our solution will not have a direct interaction with the user. These modules are obliged to provide the outputs of the interface by operating the analysis expected from them for the input parcels. Analysis modules break down as follows:

• Automatic data download module:

It is the module responsible for automatically downloading the satellite images of the agricultural parcels that are planned to be analysed, saving them in the database and preparing them for analysis. This module has undertaken the task of including every new satellite image received in the analysis without delay, thus ensuring the automatic continuous tracking.

• Soil Yield Potential Model Map:

Within the scope of our solution, the clustering of regions that are similar in terms of soil and climate characteristics has been mapped by our company according to the yield capabilities of the soils. For this purpose, soil groups classified based on yield potential have been created by making similarity analysis in terms of basic soil properties taking into account the land slope characteristics, sea height, soil depth, salinity, alkalinity, drainage insufficiency, structure, soil lime content, characteristics, and by making query models in the Geographical Information System. These maps are used during yield and loss tonnage estimation. We also have an infrastructure platform that allows similar external data to be used optionally for performance enhancement.

• Separation of parcels into subgroups (pre-process):

In addition to detecting the different product patterns in the agricultural parcel, it may be necessary to examine the sub-parcel resolution to estimate the yield according to the existence of the cultivated area and the product development. In order to meet this need, segmentation is performed within the parcel using image processing techniques. An example segmentation image is given in Figure 6.

• Product development tracking analysis module:

It is a module that enables the conversion of the development values of the products to metrics by using the multispectral reflection values obtained from the satellite images and evaluates whether the product follows the expected development process. With this analysis module, development deficiencies can be detected during the production process and reported to the relevant decision makers on a location basis. As in all analysis modules, the analysis outputs of this module, which can be accessed by the notification platform, will be reported on the information platform in accordance with the relevant user profile.

Product classification analysis module:

It is the module that calculates the attributes from the multispectral reflection values in the satellite images in the relevant parcel sub polygons as specified in the section captioned "Generating the digital signatures of product developments" and finds the product class with the best match by comparing them with the reference catalogue. As in all analysis modules, the analysis outputs of this module, which can be accessed by the notification platform, will be reported on the information platform in accordance with the relevant user profile.

• Statement control analysis module: The product in the output of the classification module in the relevant parcels is compared with the farmer's declaration obtained by various methods (farmer registration systems, third party database containing the product declaration for insurance/credit/premium, etc.). If the result of agreement with the declaration is negative, a warning is given to the operator via the information platform.

• Anomaly and Damage detection analysis module:

It is the unit responsible for finding the damages on a parcel basis in the cultivated areas, determining the amount of damage on an area basis and estimating it in tonnage and reporting it to the user. Analysis requests to this module, which does not have direct interaction with the user as in all analysis modules, are defined on the notification platform and the outputs are also reported on the notification platform. • Yield estimation module:

It is the module responsible for the estimation of the plot-based harvest amount using crop development information and soil characteristics. Analyses requests and reports are made through the information platform. · Information platform:

It is an interactive user interface where user requests of the system are defined, and analysis results are presented in the form of reports and visuals. This platform, which offers the user the opportunity to provide input to analysis modules in line with their authorizations and to examine their outputs, is designed to access the outputs of all analysis modules. Visual outputs (figures and graphics) to be given according to analysis types with reporting can also be accessed via the user platform. The information platform, developed and prototyped as a desktop application, is also designed, and developed in accordance with mobile (Android / iOS) and web platforms.

The system is based on the ideas of making decisions based on up-to-date data and automating agricultural processes using each new satellite image. For this reason, the output formats are designed to be compatible with agricultural information systems in accordance with the common GIS formats and can be opened and examined in other commercial platforms (.shp, .dbf, .tiff etc.). Since our solution does not require costly exploration methods such as installing infrastructure in production areas or using drones, it is possible to work in large areas automatically by scaling quickly. In this way, an infrastructure that can provide big data and help decision makers to see the whole will be created. In line with the above information, the invention is a method that classifies agricultural products by analysing multispectral satellite images with the help of machine learning and remote sensing techniques in order to provide agricultural decision support to users systematically and follows the phenological development of the products and is characterised in that containing these operating steps:

• Determining the type of analysis and the region to be applied as user input,

• Registering the coordinate information of the satellite image taken from the satellite image series with the corner points of the agricultural parcels (polygons),

• Segmenting the parcels according to their visual characteristics and dividing them into agricultural parcels and sub-parcels,

• Attribute calculation for each sub-parcel region,

• Generating digital signatures of product developments:

Creating a histogram from the pixel reflection values taken from each band of satellite images that coincide with the relevant parcels for the specified products,

Creating the probability density function (pdf) that gives the distribution probabilities of the pixel values for the relevant band (imaging wavelength) of the relevant satellite image of the relevant product by normalizing the histogram with the total number of pixels,

Repeating these probability density functions in all bands (wavelengths) of each new satellite image throughout the phenological phase for different samples, and recording them in time series,

Creating multidimensional features on which plant growth is modelled,

Producing probability maps containing the expected reflection values of the specific product in a particular region throughout the year as a result of this process repeated with each reference parcel obtained from the training data set,

Creating digital signatures of product developments by repeating this process for different products and different regions, • Creating soil yield potential map; climate maps and, if preferred analysis data maps by using the information provided by the statements that can be obtained from databases containing farmer information, farmer registration systems, third party database containing product declaration for insurance/ credit/premium, etc.

• Matching the attributes from the attribute calculations for each sub-parcel region, the digital signatures of the product developments and the analysis data maps data with the catalogue learned as time series,

• Classification of products by analysing the effects of reflections in different wavelengths forming satellite images based on the matched attributes throughout the phenological phase within their relations with each other, controlling the declaration by warning the operator on the information platform if the result of the agreement with the declaration is negative, by comparing the products in the output of the classification module for the relevant parcels with the farmer's declaration obtained by various methods (farmer registration systems, third party database containing the product declaration for insurance/credit/premium etc.), follow-up of development by using supervised learning methods by evaluating whether the product follows the expected development process, by using all bands of the satellite, using the multispectral reflection values obtained from the satellite images and converting the development values of the products into metrics, finding the damage in the cultivated areas on a parcel basis, determining the amount of damage on the basis of area and estimating the amount of damage in terms of tonnage and reporting it to the user, and making parcel-based yield estimation using product development information and soil characteristics

• Storage of data for each agricultural parcel,

• Visualizing the data according to the user analysis input using the information platform, analysing the data with one-year and multi-year models created by agricultural experts, and submitting agricultural decision support suggestions in line with the data. The data mentioned in the method can be stored for one year or multi-year for each agricultural parcel.

Claims

C L A I M S

1. It is a method that classifies agricultural crops by analysing multispectral satellite images with the help of machine learning and remote sensing techniques in order to provide agricultural decision support to users systematically and follows the phenological development of the crops and is characterised in that; containing these operating steps:

Determining the type of analysis and the region to be applied as user input,

Registering the coordinate information of the satellite image taken from the satellite image series with the corner points of the agricultural parcels (polygons),

Segmenting the parcels according to their visual characteristics and dividing them into agricultural parcels and sub-parcels,

Feature extraction for each sub-parcel region,

Generating digital signatures of crop developments,

Creating soil yield potential map; climate maps and, if preferred analysis data maps by using the information provided by the statements that can be obtained from databases containing farmer information, farmer registration systems, third party database containing crop declaration for insurance/credit/premium, etc.

Matching the features from the feature extraction for each sub-parcel region, the digital signatures of the crop developments and the analysis data maps attributes with the catalogue learned as time series,

Making crop classification based on the matched attributes, controlling the declaration, monitoring the crop development by using all bands of the satellite, determining anomalies and damage and making yield estimation,

Storage of the data for each agricultural parcel on an annual or multi annual basis, Visualizing the data according to user analysis input using the information platform, analysing the data with models created by agricultural experts, and submitting agricultural decision support suggestions in line with the data.

2. A method according to claim 1 and characterised in that; the storage of the data mentioned in the method is done for one year or multi-year for each agricultural parcel.

3. A method according to claim 1 and characterised in that; to present the agricultural decision support suggestions mentioned in the method to the user by providing visualization of the data according to user analysis input using the information platform and by examining the data with single-year and multi-year models created by agricultural experts, in line with the data obtained.

4. A method according to claim 1 and characterised in that; the mentioned method is to be used by all electronic devices with internet connection.

5. A method according to claim 1 and characterised in that; the stage of generating digital signatures of crop developments mentioned in the method contains these operating steps:

Creating a histogram from the pixel reflection values taken from each band of satellite images that overlap the relevant parcels for the specified crops,

Creating the probability density function (pdf) that gives the distribution probabilities of the pixel values for the relevant band (imaging wavelength) of the relevant satellite image of the relevant crop by normalizing the histogram with the total number of pixels, - Repeating these probability density functions in all bands (wavelengths) of each new satellite image throughout the phenological phase for different samples, and recording them in time series, Creating multidimensional features on which crop growth is modelled, Producing probability maps containing the expected reflection values of the specific crops in a particular region throughout the year as a result of this process repeated with each reference parcel obtained from the training data set,

Creating digital signatures of crop developments by repeating this process for different crops and different regions.

6. A method according to claim 1 and characterised in that; the crop classification mentioned in the method is done by examining the effects of reflections in different wavelengths that form satellite images based on the matched features throughout the phenological phase, in relation to each other.

7. A method according to claim 1 and characterised in that; controlling the declaration mentioned in the method is made by warning the operator on the information platform if the result of the agreement with the declaration mismatches, by comparing the crops in the output of the classification module for the relevant parcels with the farmer's declaration obtained by various methods (farmer registration systems, third party database containing the crop declaration for insurance/credit/premium etc.),

8. A method according to claim 1 and characterised in that; the crop development monitoring mentioned in the method is done by using all bands of the satellite, using multispectral reflection values obtained from satellite images, converting the development values of the crops into metrics, and evaluating whether the crop follows the expected development stages (crop phenology) by using supervised learning techniques.

9. A method according to claim 1 and characterised in that; the yield estimation mentioned in the method is to find the existence of damage on a parcel basis in the cultivated areas, to determine the amount of damage on an area basis and to report it to the user by estimating in tonnage and using crop development information and soil characteristics.

10. A method according to claim 1 and characterised in that; to make decisions based on up-to-date data by using each new satellite image and to automate agricultural processes.

11. A method according to claim 1 and characterised in that; information platform mentioned in the method provides the user with the opportunity to provide input to the analysis modules in accordance with their authorization and to examine the outputs within their authority, accessing the outputs of all analysis modules, providing visual outputs to be given according to the reporting and analysis types and can be used as a desktop, mobile (Android / iOS) or web application platform.