A Global Crop Growth Monitoring System Based on Remote Sensing
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Crop growth means the growth of cereal crop seedlings, as well as the status and trend of their growth. It has been one of the most important aspects of agricultural remote sensing in the last twenty years. Evaluation of crop growing condition in large scope before harvesting could be helpful for field management, as well as provide important information for early crop production estimation. For a country with a population of 1.2 billion it is important to know not only the domestic crop growth, but also the crop condition in other big agricultural countries that have food trade with China. This paper introduced the design, methods used and implementation of a global crop growth monitoring system, which satisfies the need of the global crop monitoring in the world. The system uses two methods of monitoring, which are real-time crop growth monitoring and crop growing process monitoring. Real-time crop growth monitoring could get the crop growing status for certain period by comparing the remote sensed data (NDVI, for example) of the period with the data of the period in the history (last year, mostly). The differential result was classified into several categories to reflect the condition at difference level of crop growing. This analysis result allows users to quickly assess how much and where conditions have either deteriorated, remained unchanged or improved. The crop growing process monitoring is the contrast between year and year for crop growth profile, which reflects the crop growing continuance at time during crop growing season. Time series of NDVI during the crop season are used and crop growth profiles are formed by getting statistical average of time series NDVI image for plowland in certain regions such as a state. Eigenvalues such as growing rate, peak value, average and so on were gotten from the crop growing profile to estimate crop growing status which concerns the whole growing process. Based on the above monitoring methods, we developed a crop growth monitoring system based on remote sensing, which provides a monitoring and analyzing environment for real-time crop growth monitoring and crop growing process monitoring to all the users. The system was developed in C/S pattern and includes five main functional modules, which are real-time crop growth monitoring module, crop growing process monitoring module, results visualization module, business management module and system configuring module. The structure and the function are particularly described in the paper. In the system, both real-time crop growth monitoring and crop growing process monitoring are carried out at three scales, which are state (province) scale, country scale and continent scale. While in most of the countries in the world the monitoring was carried out at country scale, monitoring in large agricultural countries such as USA, Canada, India, etc., was carried out at both state (province) scale and country scale. This can provide more detailed crop growth information in these countries. Much more macro crop growth information was supplied by running the system at continent scale such as North America, Europe, Africa and South East Asia, etc. Taken 10-day (16-day for MODIS) composite NDVI products of NOAA/AVHRR, SPOT/VEGETATION and MODIS as data source, the system has been run successfully for more than a year, which provides decision-supporting information on crop condition to more than a dozen of ministries and commissions in China.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it