> For the complete documentation index, see [llms.txt](https://docs.geopard.tech/geopard-tutorials/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.geopard.tech/geopard-tutorials/jpn/tsu-webapuri/geopard-mcp/dtanokurenjinguto.md).

# 収量データのクレンジングと較正

GeoPard MCPとLLMを使って、収量データセットを統計的に妥当な形でクレンジング・較正する方法を学びます。

このユースケースでは、収量データセットを用いて、圃場全体における収穫データの分布と品質を把握します。接続済みの GeoPard MCP を使うことで、LLM は元の収量データセットの統計要約を取得し、異常値やセンサーノイズを検出し、クリーニングやキャリブレーションが必要な箇所を特定します。

品質チェックが完了すると、LLM は最適なパラメータで GeoPard MCP のクリーニングおよびキャリブレーションのワークフローを起動します。

{% hint style="success" %}
このワークフローを実行する前に、GeoPard MCP が接続されていることを確認してください。セットアップの詳細は [こちら](/geopard-tutorials/jpn/tsu-webapuri/geopard-mcp/geopard-mcpwo.md).
{% endhint %}

## 単一収量データセット

{% @arcade/embed url="<https://app.arcade.software/share/Zjf8Hpwf0Ykij1Dl5r4L>" flowId="Zjf8Hpwf0Ykij1Dl5r4L" %}

### 前

<figure><img src="https://1993076779-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYICBELdyAXXebKAzfLOR%2Fuploads%2FBTboCq739Ds6EWIoN8YI%2Fimage.png?alt=media&amp;token=d7b2b51d-a67b-43c1-9a57-7e9338abc93a" alt=""><figcaption></figcaption></figure>

### 後

<figure><img src="https://1993076779-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYICBELdyAXXebKAzfLOR%2Fuploads%2FcIBWxG32gH31rkN45Cq9%2Fimage.png?alt=media&amp;token=970b3cd3-1a7c-438d-bac0-a2db73d146de" alt=""><figcaption></figcaption></figure>

## バッチ収量データセットのキャリブレーション

{% @arcade/embed url="<https://app.arcade.software/share/bibREyFI1hqQvPk7rBFq>" flowId="bibREyFI1hqQvPk7rBFq" %}

### 前

<figure><img src="https://1993076779-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYICBELdyAXXebKAzfLOR%2Fuploads%2FUATNQLP0u88zsnlLkAAm%2Fimage.png?alt=media&amp;token=a85329be-0cb9-4c38-88c5-8b591638edf9" alt=""><figcaption></figcaption></figure>

### 後

<figure><img src="https://1993076779-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYICBELdyAXXebKAzfLOR%2Fuploads%2Fimu4ak8G06puVVlpSS6w%2Fimage.png?alt=media&amp;token=51ec2b97-fa4e-403a-af7c-e68506a872c7" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.geopard.tech/geopard-tutorials/jpn/tsu-webapuri/geopard-mcp/dtanokurenjinguto.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.