Cotton farming industry development and policy finance support for demand estimation in Aksu

Abstract

Using data mining, the purpose of this study is to forecast and analyze the growth of the cotton cultivation industry and the policy financial support demands in the Aksu region. Data mining is a method for maximizing the value of data via the application of numerous algorithms. In contrast to conventional data mining, which adheres to specific algorithms, data mining employs a variety of analysis algorithms to analyze raw data, such as image and panel data, and produce accurate results. In this paper, we propose a data mining method that combines the semantic segmentation algorithm of remote sensing images with various nonlinear regression algorithms to predict the demand for policy-based financial support in a specific region based on a combination of multiple factors, including agricultural crop cultivation area, catastrophe analyses, agricultural price and inflation rates, etc. This paper intends to estimate and analyze actual data pertaining to the cotton cultivation industry in Aksu, and this methodology can further improve the policy-based financial inverse model. The methods presented in this paper can further improve countercyclical regulation of policy finance.

Keywords

Policy finance deep learning data mining agricultural economy

1. Introduction

As the country’s primary industry, it is self-evident that agricultural production work plays a crucial role in its economy. It should be noted that, as part of the continued strengthening of the national strategy for rural revitalization, the state has steadily increased financial support for rural areas. Due to the peculiar characteristics of rural finance, such as information asymmetry and high contract costs, general financial institutions rarely provide financial assistance to farmers, and government-sponsored policy financial assistance has become an important tool for the regulation and control of agricultural production. Effectively forecasting policy-based financial support can enhance policy-based financial support on the ground, thereby contributing to the expansion of agricultural work in China.

The need for a high level of model interpretability is the impetus for the problem investigated in this paper. This paper proposes a new data mining method that combines deep learning and machine learning algorithms, and applies it to the most important cotton-producing region in our country, the Aksu region. This method will be useful for future agricultural finance research.

2. Review of the literature

Modern researchers have been confronted with a number of difficult questions. Academics continue to investigate and analyze the many facets of rural finance now that its development is well under way. Clearly, they note that financial support can alleviate financial inhibitions in certain counties to a certain extent, and that this alleviation has a greater impact in densely populated and economically developed regions [1]. Guijun Zhang and Minhua Ouyang used the propensity matching method to analyze the income enhancement status of rural households and found that policy-based financial programs increase the disposable income of low-income households [2]. By applying the Oaxaca-Blinder decomposition method to insurance, banking, and Internet finance, Fang Su and Lei Fang investigated the underlying causes of supply exclusion, self exclusion, no demand, and physical exclusion in financial exclusion [3] and obtained promising analytic results.

The preceding studies provide a statistical analysis of agricultural finance issues, from which clear conclusions can be drawn. Nonetheless, if the data for model analysis come from statistical yearbooks, regional panel data, or data from banks on their own, the model loses its predictive power and can only perform statistical analysis on data that becomes available after the publication of yearbooks and panel data, which is typically at the beginning of the following year; thus, it has lost its early warning capability.

In the field of policy finance, increasing the accuracy of forecasting capabilities has been a valuable tool for addressing crises and rationally organizing capital operations. Similarly, it is possible to provide immediate financial aid in the event of a natural disaster or a bountiful harvest. For economic forecasting models, the academic community typically employs a linear or nonlinear forecasting algorithm. Song Lian, for example, suggested using the nonlinear gray model (GM) (1, 1). Even after accounting for independent variables such as fertilizer, labor, water, and electricity, the Aksu cotton production forecast for 2020 still contains an error rate of more than 100,000 tons [4]. On the basis of single linear or nonlinear prediction algorithm, although some scholars have studied the method of adding remote sensing images and then using basic NDVI parameters and SAR parameters for image analysis, trying to accurately predict the yield of planting industry. For example, VN Sridhar et al. predicted the yield of wheat in Madhya Pradesh from 1991 to 1992, and used the RVI parameters of remote sensing images to identify on the basis of ARIMA model, that the results are still unsatisfactory. The yield error of wheat in 1992 was as high as 60.02% [5]. J. Betbeder et al. proposed SAR parameter estimation for the yield estimation of rapeseed and wheat through remote sensing, but its effect did not show a consistent improvement in the performance of the two crops (compared with NDVI parameter method) [6]. The reason is that the prediction error of planting area produced by the above research based on the regularization method of processing remote sensing images is large. Therefore, when combining the output of unit output to predict the output, there is a large prediction error compared with the actual output. It also prevents the current scholars from further exploring the deeper research such as the prediction of the output value of planting industry. At the same time, previous studies also face the interference brought by time series to varying degrees, and there is a problem of model failure in long-span prediction.

Using data from previous years for forecasting current production output, regardless of the data’s quality or number of variables, makes forecasting more difficult as the time span increases. Due to disaster cycle fluctuations, changes in planting scale, crop market fluctuations, and other factors, determining how to more accurately predict the output of the cotton plantation industry in advance has become a pressing financial policy issue. The paper proposes a new high-precision plantation forecasting method after exhaustively examining the limitations of existing plantation forecasting methods. Initially, during the cotton planting process, the cotton plantation area is analyzed by the semantic segmentation algorithm of remote sensing images, and the yield is predicted based on variables including time series fluctuations in plantation area and disaster cycle fluctuations. This method is more accurate than those that rely solely on data from previous years, and it also uses remote sensing images at various stages of the planting process to predict crop yield. This paper compares the remote sensing images of cotton fields at different stages between 2013 and 2019 to analyze the yield of disaster reduction using remote sensing images from different periods of the planting process. This paper attempted to predict the output value of the cotton planting industry from 2014 to 2019 by calculating the output value using the price-value system, inflation coefficient, and yield per unit area in order to conduct a comprehensive analysis of the output value of the cotton planting industry. These results demonstrate that the proposed method can accurately predict the output value of the cotton plantation industry in the region before the yearbook is published, and that the predicted financial support demand is conducive to the sound and orderly development of the cotton harvesting and deep processing industries, as well as to the policy financial institutions’ efforts to further control risk and improve their capacity to serve agriculture.

3. Aksu cotton yield prediction based on time series analysis of remote sensing images

Utilizing remote sensing images for yield estimation has become an increasingly popular method of remote sensing image application in agriculture. Various index systems for multispectral image analysis are used in traditional satellite image processing, with the Normalized Difference Vegetation Index (NDVI) or Ratio Vegetation Index (RVI) being the most frequently used one in remote sensing image yield estimation, as shown in Eq. (1).

$\displaystyle\left\{{\begin{array}[]{l}\text{NDVI}=\frac{(NIR-R)}{(NIR+R)}\\ \text{RVI}=\frac{NIR}{R}\\ \end{array}}\right.$ (1)

Both NDVI and RVI methods in Eq. analyze surface properties by comparing the near-infrared band to the red band, where NIR represents the value of the near-infrared band reflection and R represents the value of the infrared band reflection. In general, if the IR band reflection value is high, the density of vegetation is high, and vice versa, the vegetation cover may be sparse or have died for a variety of reasons if the value is low. The NDVI and RVI indices have a strong correlation for predicting crop yields because crops are typically planted at high densities. This made vegetation indices the primary method for assessing crop planting until the development of deep learning algorithms. However, images of sparse vegetation captured by remote sensing could be the result of natural disasters, pests, or diseases. In addition, other non-target crops, green landscapes, geothermal sources, and other non-crop interference situations may also contribute to dense vegetation. Consequently, using simple exponential calculation methods directly in practical applications can be error-prone, as the identified area is typically much larger than the annual statistics. In a study conducted by Sijia Li, the NDVI index was utilized to estimate the prediction of maize yield in Lishu County, with the predicted results in many years exceeding the actual results. In 2010, for example, the predicted area was 114769 ha, while the actual area was 97003 ha [7]. He Fuwei calculated the winter wheat planting area in North China by normalizing the LAI from remote sensing images and analyzing the yield and total yield by combining data from agricultural monitoring stations; the results were comparable to reality [8]. In recent years, multispectral remote sensing image recognition has gradually surpassed traditional image processing algorithms in terms of accuracy and recall, thanks to the progressive development of deep learning technology. Deep learning algorithms are able to recognize complex texture features in images and have strong generalization capabilities, allowing them to gradually replace complex image recognition analysis [9]. Hao-Lu Li, for instance, used the enhanced DenseNet to segment and identify the planted area of cotton fields in Kuche County, Xinjiang, and then used NDVI, wind speed, and precipitation to analyze the yield after calculating the yield, employing the ConvGRU algorithm to predict the yield error in recent years about 200 kg/ha and the total yield error about 4 $\times$ 10 ${}^{4}$ tons [10]. It is worth noting that 96% yield prediction results for the years 1993 to 2018 are higher than the yearbook’s published production. This also illustrates the issues associated with the current direct application of deep learning to predict planted area.

In light of the aforementioned examples, it is not difficult to identify a dearth of current research.

First, the area identified by remote sensing images is directly compared with the planting area and other government-published information, ignoring the possibility that the identification results in remote sensing images have a linear relationship with the actual planting area (e.g., some misidentified image elements may continue to be misidentified in future images, causing a linear error in the predicted planting area).

Second, the cyclical variation data of natural disasters was not incorporated into the pattern of temporal variation of planted area.

Thirdly, neither the CPI, production, nor crop price forecasting analyses nor the work on production value forecasting were analyzed.

Fourth, the analysis was not aligned with policy-based financial requirements, and the projection results were not translated into substantial agricultural development instruments.

Despite the use and improvement of numerous advanced algorithms in deep learning, the current research has low prediction accuracy, is not integrated with rural agricultural development requirements, and is primarily focused on yield prediction.

This paper proposes a more accurate deep learning algorithm, Cascade-PSPNET image segmentation, for remote sensing images in order to accurately identify crop planting at the pixel level. We have computed yield estimates using ARIMAX and multiple precipitation, wind, NDVI, and seed quality factors. The loss area is determined by the linear relationship between the predicted area of a time series and the disaster-affected area. The yield prediction accuracy is further enhanced by the linear regression correction between the predicted yield and the actual yield, and the next step is to develop a production forecast while providing financial support. A two-stage object detection model, was proposed to solve the problem of detection area discovery through different threshold output, improve the accuracy of object detection, and was improved several times in subsequent studies [11]. At the same time, as the current classic remote sensing image semantic segmentation network, PSPNET has a good effect on the segmentation of regions of different sizes because it uses a pyramid pooling layer to carry out different scales on the middle features of the network [12]. This paper attempts to combine the advantages of the two networks, and proposes Cascade-PSPNET through the combination of threshold division technology and PSPNET network structure, hoping to further improve the recognition ability of semantic segmentation network for remote sensing images.

4. Cascade-PSPNET and production and production forecasts

It is essential to determine the time-phase of images gathered by remote sensing to accurately estimate crop yields. According to their production areas and climates, the cotton-producing regions of Xinjiang can be divided into eastern Xinjiang, southern Xinjiang, and northern Xinjiang. The southern region of Xinjiang is distinguished by ample sunlight and a longer frost-free period. The cotton-growing region of Aksu is located in southern Xinjiang. According to local meteorological observatories, media reports on sowing date forecasts, and agricultural reports, the optimal sowing date is typically around mid-April, prior to and following the Grain Rain [13, 14]. The seeds germinate approximately 15 days after sowing. The blooming period occurs between the beginning and middle of July. Generally speaking, early September is harvest time in southern Xinjiang, while early October is harvest time in northern Xinjiang. In the region of Aksu, harvest typically occurs between late September and early October. Cotton varieties are grown for a variety of purposes, including lint, upland, and long-staple cotton. There is no significant difference between these varieties’ planting cycles. Additionally, wheat and maize are the principal crops of the Aksu region. The planting area for spring wheat in 2021 [15] is 2.75 million mu, spring wheat is 30,000 mu, winter wheat is harvested in April and May, and spring wheat is harvested in August, according to statistical data. Similarly, the corn harvest occurs at the end of August. The optimal months for acquiring remote sensing images are therefore early June and early September. Winter wheat is typically harvested in early June, while corn is typically planted in the middle of June. Thus, other crop characteristics can be excluded more efficiently. Spring wheat and corn are harvested in early September, and cotton is nearing harvest. Therefore, identifying cotton planting characteristics in remote sensing images is advantageous. The schematic diagram of remote sensing phases and time is shown in Fig. 1.

Figure 1.

Diagram of remote sensing image time phase selection.

It is difficult to apply the Cascade-PSPNET image segmentation algorithm proposed in this paper to achieve pixel-level semantic segmentation because a selection of June images cannot eliminate the overlap of winter wheat harvesting and corn planting stages. Four channels of green and near-infrared bands are trained through the visible light band and near-infrared band’s characteristics and have the ability to identify different types of plants. Figure 2 illustrates the application of the Cascade-PSPNET structure to multispectral remote sensing images as described in this paper.

Figure 2.

Res-Conv structure.

Based on Eq. (2), each residual head is assigned the binary loss function Focal-Loss, and the total loss function Loss-total of the first-stage network is equal to the sum of the three residual head loss functions Final-Loss. The Focal-Loss formula in Eq. (2) $\alpha_{t}$ denotes the inverse category frequency of positive and negative samples, which is equivalent to the positive and negative samples’ own weights. $p_{t}$ indicates the confidence level of the model itself for the sample classification prediction, and the model output in the binary Focal-Loss will be the highest confidence of 1 for the positive category and the lowest confidence of 0 for the negative category, such that $p_{t}$ has the expression given in Eq. (2).

$\displaystyle p_{t}=\left\{{\begin{array}[]{ll}p&\text{if }y=1\\ 1-p&\text{otherwise}\\ \end{array}}\right.$ (2)

Table 1

Cascade-PSPNET network parameters table

Stage	Output	Cascade-PSPNET
Conv1	112 $\times$ 112	7 $\times$ 7, 64, stride2
		3 $\times$ 3, max pooling, stride2
Conv2	56 $\times$ 56	$\left[{\begin{array}[]{l}1\times 1,128\\ 3\times 3,128,C=32\\ 1\times 1,256\\ \end{array}}\right]\times 3$
Conv3	28 $\times$ 28	$\left[{\begin{array}[]{l}1\times 1,256\\ 3\times 3,256,C=64\\ 1\times 1,512\\ \end{array}}\right]\times 4$
Conv4	14 $\times$ 14	$\left[{\begin{array}[]{l}1\times 1,512\\ 3\times 3,512,C=64\\ 1\times 1,1024\\ \end{array}}\right]\times 6$
Conv5	7 $\times$ 7	$\left[{\begin{array}[]{l}1\times 1,1024\\ 3\times 3,1024,C=32\\ 1\times 1,2048\\ \end{array}}\right]\times 3$
Features	1 $\times$ 1	Global average pooling
Params	21.9 $\times$ 10 ${}^{6}$

To train the Cascade-PSPNET two-stage network, the Res-Conv4 residual convolution module is used. The second-stage loss function is a single binary Focal-Loss function with a threshold of 0.5 to output the final fused segmented images. This design concept has been developed based on the advantages of the two-stage network. In the target detection network, the Cascade-RCNN network has advantages over other two-stage networks because the first stage employs multiple thresholds to effectively deal with difficult-to-score samples, thereby reducing the imbalance in the output of the feature map in the first stage. The second-stage network analyzes the classification problem, thereby removing the issue of an excessive number of negative samples during the target detection stage. When it comes to frame and pixel segmentation metrics, the semantic segmentation and target detection algorithms have many similarities; both can use metrics such as IOU to assess location accuracy and category loss to assess the classification accuracy of a single frame or pixel and perform a comprehensive analysis. Therefore, attempting to incorporate Cascade’s two-stage network structure into the conventional segmentation model is worthwhile. There are a number of parameters in each stage of the model depicted in Table 1, and the total number of parameters in this paper is 21.9 $\times$ 10 ${}^{6}$ , making it a model of moderate complexity.

Taking into account model training data sources, this study should analyze multispectral remote sensing images for crop identification in order to better distinguish crop status, and remote sensing images should account for multiple factors affecting identification accuracy, such as spatial resolution, cloud cover, band, satellite strip width, and return period. Lantsat8 and Gaofen-1 provide the best resolution accuracy, return period, band and strip width among current civil high-precision satellites, and both can be acquired through commercial and educational channels. A detailed comparison is shown in Table 2.

Table 2

Comparison of high-resolution civil satellite images

Comparison category	High score one	Lansat8
Strip width	800KM	185KM
Spatial resolution	16 m	30 m
Return visit cycle	4 days	16 days
Red light band	630 $\sim$ 690 nm	640 $\sim$ ‘670 nm
Green light band	520 $\sim$ 590 nm	530 $\sim$ 590 nm
Blue wavelengths	450 $\sim$ 520 nm	450 $\sim$ 510 nm
Infrared band	770 $\sim$ 890 nm	850 $\sim$ 880 nm

Gaofen-1 has a greater advantage, primarily due to its short return period, which makes it possible to intercept remote sensing images for stitching within a short period of time, preventing cloud cover from causing errors in the determination of the planting surface. Lansat8, on the other hand, has a 16-day return period, making it easy to miss the most advantageous time period. In addition, the strip width of the Weigan River Oasis is 322 kilometers north to south and 194 kilometers east to west, which is greater than the strip width of Lansat8. Therefore, the Gaofen-1 satellite image for 2015-2021 is chosen as the input image, and the Weigan River Oasis in the Aksu region with the latitude and longitude ranges (41 ${}^{\circ}$ 01’N41 ${}^{\circ}$ 43’N 82 ${}^{\circ}$ 09’E83 ${}^{\circ}$ 25’E) is chosen as the target area. It is geographically located at the northern tip of the Tarim Basin, in the southern region of Xinjiang, and comprises three administrative divisions: Kuche, Xinhe, and Shaya counties. In order to accommodate the output model of this paper, the original multispectral image captured by the satellite is cropped to 256 by 256 pixels during the image processing session. Second, the cotton fields are annotated using the non-overlapping polygon annotation method at the pixel level. Overall, 16547 annotated images were divided into 90% of the training set and 10% of the test set. The image enhancement methods used are shown in the pseudo-code.

Set image training set $P_{\textit{train}}=\{p_{t1},p_{t2},p_{t3},\cdots\}$ , training attribute set $M_{\textit{train}}=\{m_{t1},m_{t2},m_{t3},\cdots\}$ , image test number set $P_{\textit{test}}=\{p_{te1},p_{te2},p_{te3},\cdots\}$ , test attribute set $M_{\textit{test}}=\{m_{te1},m_{te2},m_{te3},\cdots\}$ .

While Model is Training:#While Model is Training

For $p_{t}$ , $m_{t}$ in ( $P_{\textit{train}},M_{\textit{train}}$ ):#For training set images and labeled Mask $p_{t},m_{t}=$ VerticalFlip ( $p_{t},m_{t},p=$ 0.5)#VerticalFlip $p_{t},m_{t}=$ horizonFlip ( $p_{t},m_{t},p=$ 0.5)#HorizontalFlip $p_{t},m_{t}=$ ShiftScaleRotate ( $p_{t},m_{t},p=$ 0.5)#ScaleRotate $p_{t}=$ Blur $|$ Shapen ( $p_{t},p=$ 0.5)#Gaussian blur or sharpen $p_{t}=$ GaussianNoise ( $p_{t},p=$ 0.5)#Gaussian noise $p_{t}=$ GaussianNoise ( $p_{t},p=$ 0.5)#Gaussian noise $p_{t}=$ RandomBrightness ( $p_{t},p=$ 0.5)#RandomBrightness Return $P_{\textit{train}},M_{\textit{train}}$

In the field of image enhancement, this paper introduces the concept of combining probability and image enhancement methods. For instance, after vertical flipping with a random probability of 0.5, the image has a 50% chance of becoming either the top or bottom mirror image or the original mirror image, and after horizontal inversion, the image may or may not be vertically flipped, which greatly improves the data set for spatially dense distribution. Since the semantic segmentation of images in this study is a position-sensitive task, flipping the images may improve the robustness of the model for pixel position judgment, and a 10% random brightness noise is added to the image enhancement process to improve the recognition effect under different lighting conditions and seasonal changes. Thus, the spatial distribution of the data set has been significantly enhanced.

In terms of parameters, training parameters were set using gradient descent optimization for Adamw, and the training parameters as well as evaluation indexes (IOU, F1Score, Focal Loss value, etc.) are shown in Table 3.

Table 3

Comparison of training parameters and model metrics

Network name	Cascade-PSPNET	UNET $++$	U ${}^{2}$ NET
lr	0.001	0.001	0.001
Decay	0.01	0.01	0.01
IOU	0.79	0.67	0.71
F1Score	0.81	0.78	0.79
Focal loss	0.65	1.12	0.78

The comparison of this model’s segmentation effect to that of similar models trained with the same parameters in Table 3 demonstrates the sophistication of this model. By incorporating Focal-Loss, it is possible to assess the classification status of the model’s challenging samples. While the two-stage segmentation model presented in this paper slightly increases the model’s computational volume and number of parameters, it outperforms similar segmentation models in a variety of indexes and has significant application potential.

In this paper, the trained Cascade-PSPNET network and other comparison networks are used to compare the cotton field area recognition effect in random image images, as shown in Fig. 3 of the model comparison image recognition effect graph. On Fig. 3, the original image is depicted in pseudo-color, and the recognition effect of the text-trained Cascade-PSPNET, UNET $++$ , and U2NET networks for the edge and internal hole processing effects of the Cascade-PSPNET network proposed in this paper can be clearly observed.

Figure 3.

Results of cotton fields identified by different models with original images: (a) pseudo-color multispectral remote sensing images, (b) cotton field mask labels, (c) Cascade-PSPNET, (d) UNET $++$ , (e) U ${}^{2}$ NET. Identified cotton field identification results. Black is the background, white is the identified cotton field.

Figure 3 shows the comparison between the planting area and the actual planting area of Aksu Region in all years between 2014 and 2019 (from the manual statistics of the Xinjiang Statistical Yearbook). The results of the analysis of Table 3 combined with Fig. 3 can be found in the remote sensing image recognition results. Some fixed recognition error image elements are easily misidentified as cotton fields, resulting in an overestimation of the cotton field recognition area. Therefore, it can be inferred that there should be a first-order linear relationship between the identified cotton field area and the actual cotton field area, and that neither the bias term nor the weight term should be zero.

Furthermore, since the cotton yield in Aksu region is adversely affected by major disasters such as hailstorms, mudslides, windy weather and heavy rainfall throughout the year, the timing of these disasters is unpredictable and difficult to predict. As a result, a prediction method is applied to complete the first-order residuals. Since current methods of forecasting acreage include LSTM, GRU, and other neural network methods, but the amount of data in this paper is too small, making it very easy for neural networks to overfit and thereby making future predictions difficult, this study attempts to predict the primary term residual of the current acreage by ARIMAX by using the fluctuation of acreage and disaster area from June to September in order to more precisely estimate the acreage. As shown in Eq. (3),

$\displaystyle\left\{{\begin{array}[]{l}M_{{ca}}=w_{1}a_{ca}+b_{1}+o(a_{ca})\\ o(a_{ca})\approx\text{ARIMAX}((A_{9}-A_{6}),A_{a})\\ \end{array}}\right.$ (3)

Where $M_{{ca}}$ denotes the real area that should be predicted and $w_{1},b_{1}$ denotes the weight and bias. $a_{ca}$ denotes the cotton planted area predicted by using deep learning in this paper. The acreage fluctuation from June to September ( $A_{9}-A_{6}$ ) and the damage loss $A_{a}$ statistically predicted acreage residuals make the ARIMAX predicted value close to $o(a_{ca})$ . Figure 4 displays the predicted cotton acreage results using the Eq. (3) method for the period 2014–2019 based on the results predicted by this formula.

Figure 4.

Comparison of deep learning recognition prediction results and correction results of Eq. (3).

Since the relationship between area unit yield $=$ total yield and total yield unit price $=$ production value already exists, this paper extends this method cyclically to yield prediction and production value prediction to compensate for the possible bias resulting from repeated prediction via the cyclic residual prediction mechanism. In one example, after multiplying the output data by the average yield and the area predicted in this article, forecast residuals from previous yields and yield factors are used to make the predicted value of ARIMAX approximate to $o(y)$ , and this method is applied repeatedly in order to predict the final output value. As shown in Eq. (4), the planting area has been extended to yield $Y_{ca}$ . As shown in Eq. (4), $w_{2}$ is the planting yield and $b_{2}$ is the supplementary offset. $o(w_{2},M_{ca})$ indicates the residual that needs to be predicted and filled. Residuals also use ARIMAX for prediction completion, and $w_{2}$ is one of the ARIMAX parameters.

$\displaystyle\left\{{\begin{array}[]{l}Y_{{ca}}=w_{2}M_{ca}+b_{2}+o(w_{2},M_{% ca})\\ o(w_{2},M_{ca})\approx\text{ARIMAX}(w_{2},M_{ca},A_{a})\\ \end{array}}\right.$ (4) $\displaystyle\left\{{\begin{array}[]{l}V{}_{ca}=w_{3}Y_{ca}+b_{3}+o(w_{3},Y_{% ca})\\ o(w_{3},Y_{ca})=\text{ARIMAX}(w_{3},Y_{ca},c_{ia})\\ \end{array}}\right.$ (5)

This is then combined with $Y_{ca}$ in Eq. (4) and extrapolated to Eq. (5) for the production value forecast $V_{ca}$ . It is worth noting that $w_{3}$ in Eq. (5) is similar to Eq. (4) and $w_{3}$ is the unit price of cotton, which is used to multiply with production. The bias is $b_{3}$ and in the residual $o(w_{3},Y_{ca})$ , the inflation factor $c_{ia}$ is taken into account with the cotton unit price $w_{3}$ and in Eq. (5) $o(w_{3},Y_{ca})$ is used to forecast the production value forecast, which serves a good purpose. Under this systematic approach, the experimental example of the method proposed in this paper is shown in Section 4.

Figure 5.

Financial support forecasting system solution.

5. Analysis of cotton industry-related forecast results and financial support

Figure 5 depicts the flowchart for the financial support system based on the data mining methodology proposed in this paper. In the first section of this paper, node 1 completes the preliminary prediction for cotton planting area, node 2 completes the accurate prediction for cotton planting area, node 3 completes the accurate prediction for cotton yield, and node 4 completes the accurate prediction for cotton production value. In order to achieve the objective of accurate financial support estimation, the scheme incorporated the concept of residual neural networks by utilizing cross-layer variables and removing residuals.

The residual prediction complementary method presented in this paper is employed in node 5 for the analysis, and the amount of financial support required in this year’s Aksu region is predicted by the same method using unit prices, the amount of financial support in previous years, and taking inflation into account, as shown in Eq. (6).

$\displaystyle\left\{{\begin{array}[]{l}S{}_{fi}=w_{4}V_{ca}+b_{4}+o(w_{4},V_{% ca},c_{ia})\\ o(w_{4},V_{ca},c_{ia})=\text{ARIMAX}(w_{4},V_{ca},c_{ia})\\ \end{array}}\right.$ (6)

In Eq. (6), $S_{fi}$ is the financial support, the residual $o(w_{4},V_{ca},c_{ia})$ is also made up using ARIMAX forecasting, and $c_{ia}$ is still the inflation coefficient. In this paper, ARIMAX algorithm is used as an autoregressive algorithm with multiple outputs, so the input sequence needs to meet the requirements of a stable sequence. Because there is a certain linear relationship between cotton planting area – yield – output value in Aksu region in the previous studies, it can be equivalent to “converting to a stable sequence by determining the trend method” in the system scheme in Fig. 5, but the lack of research on the residuals $o(w_{4},V_{ca},c_{ia})$ in Eq. (6) shows that they belong to a stable sequence, In order to further ensure the rationality of this paper, ADF test method is used to confirm that the linear regression residuals belong to stationary series. As shown in Fig. 6, the results of ADF test and 1%, 5% and 10% show that the assumption of non-stationary sequence can be rejected, and the $p$ value of the sequence is close to 0, so the sequence can be regarded as a stationary sequence.

It is worth noting that there is a simple linear relationship between acreage, yield, and output in Eqs (3)–(6). The linear relationship between policy financial support and output value has not been demonstrated in previous studies, but Fig. 6 has verified the stable sequence relationship of residuals, so the rationality of using ARIMAX is fully guaranteed. Finally, this paper analyzes the linear relationship between the loans of financial institutions and the output value of the cotton industry through $R^{2}$ verification, and obtains that the fitting regression coefficient $R^{2}=$ 0.77 basically conforms to the linear condition, so the overall assumption of this paper is correct.

Figure 6.

$o(w_{4},V_{ca},c_{ia})$ ADF test.

Table 4 provides a summary of the methods that will be used in this paper to predict financial support based on the algorithm flow depicted in Fig. 5. The parameters of $w, b$ calculated by the algorithm flow depicted in Fig. 5 are also provided.

Table 4

Algorithm flow parameters table

Parameters	Value
$w_{1}$	0.95
$b_{1}$	234.223
$w_{2}$	147
$b_{2}$	$-$ 6374.91
$w_{3}$	22.5
$b_{3}$	323652.86
$w_{4}$	$-$ 0.02
$b_{4}$	63.67
$c_{ia}$	2%

Figure 7.

Loan forecast error curve for financial institutions by algorithm over the years.

According to the same method, the amount of financial assistance needed in the Aksu region this year was predicted by using cotton yields, unit prices and production output values, as well as the amount of financial assistance provided in the cotton farming industry in the previous year, and taking inflation into account. This forecast is based on Xinjiang Statistical Yearbook data from 2013–2018 (Open source public release) [20] and satellite images of the corresponding time period. Forecasts are made for data from 2014–2019. The analysis results are shown in Fig. 7, which illustrates the prediction results of this paper regarding financial support and crop output. As evidenced by the results of previous years, the financial support prediction method proposed in this paper has significantly improved accuracy in almost all years compared to linear regression and ARIMA prediction, and the final predicted MAE has reached the level of applicability. It has a high potential for application.

5.1 Summary

This paper preliminarily summarizes the methods of predicting the output value of planting industry in the previous studies, and analyzes why the current research has not completed the full link prediction from predicting the planting area – output value – to further financial support quota of planting industry. The root cause lies in the prediction deviation of planting area, which makes it difficult to obtain high accuracy of link prediction. In order to better complete the fine planting area prediction, inspired by the network structure of CascadeRCNN and PSPNET, this paper proposes Cascade-PSPNET to complete a more accurate planting area prediction, which improves at least 5% IOU compared with other semantic segmentation algorithms, so that the prediction yield and prediction output value goals proposed in this paper have been achieved. Finally, by using the concept of residuals, this paper constructs an automated sequence stabilization method, which extends and reorganizes the ARIMAX prediction link to form a financial prediction system scheme, and achieves the goal of accurately predicting the total amount of policy financial support for the cotton planting industry in the Aksu region. This paper hopes to provide a new perspective and method for agricultural financial analysis.

References

. Agriculture policy finance supply and rural financial disincentives – empirical evidence from 147 counties. Financial Research. 2015; (2): 12.

Zhang

Ouyang

. Evaluation of income improvement effects of policy-based financial poverty alleviation projects – Jiangxi Province as an example. China Soft Science. 2018 Apr; 000(004): 54-64.

Fang

. Regional differences in financial exclusion in rural China: Insufficient supply or insufficient demand? – A comparative analysis of banking, insurance and internet finance. Management World. 2016; (9): 14.

Xie

Yang

. Analyses and early warnings of cotton prices in Xinjiang’s Aksu region using the ARIMA model. Rural Economy and Technology. 2016; 30(19): 3.

Sridhar

Dadhwal

Chaudhari

, et al. Wheat production forecasting for a predominantly unirrigated region in Madhya Pradesh India. REMOTE SENSING. 1994; 15(6): 1307-1316.

Betbeder

Fieuzal

Philippetsa

, et al. Estimation of crop parameters using multi-temporal optical and radar polarimetric satellite data. Spie Remote Sensing. 2016.

. Remote sensing estimation of maize yield in Lishu County, Songnen Plain based on TM images. Science and Technology Innovation. 2021; 15(12): 2.

. A study on the estimation of winter wheat yield using the APSIM model and remote sensing data. Agriculture and Technology. 2022; 42(4): 6.

Huang

Liu

, et al. Regional winter wheat yield prediction based on remote sensing information and crop model ensemble Kalman filter assimilation. Journal of Agricultural Engineering. 2012; (04): 142-148.

10.

. Research on remote sensing identification and yield prediction of cotton fields in Xinjiang based on deep learning. Nanjing University of Information Science & Technology. 2021.

11.

Cai

Vasconcelos

. Cascade R-CNN: Delving Into High Quality Object Detection. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; 2018.

12.

Zhao

Shi

, et al. Pyramid Scene Parsing Network. IEEE Computer Society. 2016.

13.

Yang

. A study of the mechanism and path of the role of rural finance in rural economic growth in Xinjiang. Xinjiang Agricultural University. 2018.

14.

Ding

Zhang

Gao

. Identification of rural financial factors that affect rural economic development based on regional economic differences. China Rural Economy. 2014; (3): 11.

15.

Yuxuan

Mengfei

Shusen

. Analysis of the role of rural financial services in fostering the economic transformation and upgrading of the “three rural areas”. Shanxi Agricultural Economics. 2022; (2): 3.

16.

Liu

. An empirical analysis of the relationship between rural financial development and rural economic growth in Heilongjiang Province. Econosmic and Technical Cooperation Information. 2021; (17): 1.

17.

Yang

. Research on the mechanism and path of the role of rural finance on rural economic growth in Xinjiang. Xinjiang Agricultural University. 2021.

18.

. Enhancing the inclusiveness of rural revitalization in order to promote the common prosperity of rural farmers. China Rural Economy. 2022; (02): 2-14.

19.

. Study on the optimization of China’s rural financial organization system. Southwest University. 2009.

20.

National Bureau of statistics. China Statistical Yearbook. Beijing: China Statistics Press; 2013–2018.