CropWatch Monitoring Indicators and Methodologies

The current CropWatch system has established a comprehensive framework of remote sensing indicators and methodologies for monitoring crop condtions  throughout the entire growing season. In the future, with the continuous enrichment of multi-source data and the advancement of intelligent technologies, CropWatch will keep evolving toward more intelligence, providing better technical support for agricultural information accessibility and food security.

1. CropWatch Indicators

CropWatch indicators are used to assess agri-climate as well as crop conditions and dynamics. Four major categories of indicators are employed to analyze crop performance across different spatial units:

(i) Agro-climatic indicators, which reflect the potential impacts of weather factors—such as rainfall (RAIN), temperature (TEMP), and photosynthetically active radiation (PAR)—on crop growth, as represented by the potential biomass accumulation (BIOMSS);

(ii) Remote sensing–based agronomic indicators, which describe the actual growth conditions of crops, including the Normalized Difference Vegetation Index (NDVI), the Vegetation Health Index (VHI), the Cropped Arable Land Fraction (CALF), the Maximum Vegetation Condition Index (VCIx), and the Cropland Intensity Index (CI);

(iii) Yield indicators, which quantify the three core components of crop yield—planting area, yield, and total production.

(iv) Early warning indicators, which reflect the overall status and outlook of agricultural production, such as the Crop Production Index (CroPI), the Agricultural Drought Area Change Index (ADAC), and the Palmer Drought Severity Index (PDSI).

2. Remote Sensing Monitoring of Crop Planting Area

CropWatch comprehensively considers regional differences in agroecological system, cropping structure, farmland management, and ground observation data, and has established an operational crop area monitoring system based on agroecological zones as the basic unit. The system adopts a microservices architecture, encapsulating multiple crop identification and classification techniques—such as the mapping index of soybean, maize and rapeseed, random forest classification, sample-free and small-sample crop classification, spatiotemporal transfer classification, and a two-step method for rice potential area identification and fine extraction—into APIs for modular and scalable services.

By integrating semantic segmentation and artificial intelligence models, the system enables efficient data cleaning and high precision crop type identification. Meanwhile, the combination of large scale crowdsourced data and multiple classification algorithms supports crop mapping in major grain and oilseed producing and exporting countries. Furthermore, by integrating high resolution field parcel extraction results with cropland distribution data, non-cropland coefficients are quantitatively assessed and combined with crop mapping results to achieve high-precision dynamic monitoring of crop planting areas.

3. Methods for Crop Yield Monitoring and Forcasting

CropWatch employs multiple approaches for crop yield estimation, including the yield–remote sensing index model, the biomass–harvest index model, and various data-driven methods. By coupling crop spatial distribution, phenological information, and the biomass–harvest index model, CropWatch has developed an interactive and visualized crop yield prediction system, enabling dynamic monitoring and assessment of yield for target crops.

For more details, please visit: http://cloud.cropwatch.com.cn/web/method

Reference

• 
  

  Bingfang Wu, Miao Zhang, Hongwei Zeng, et al. (2023). Challenges and opportunities in remote sensing-based crop monitoring: A review. National Science Review, 10(4), nwac290. doi:10.1093/nsr/nwac290

• Bingfang Wu, Fuyou Tian , Mohsen Nabil, et al. (2023). Mapping global maximum irrigation extent at 30m resolution using the irrigation performances under drought stress. Global Environmental Change, 79, 102652.

• Fuyou Tian, Bingfang Wu, Hongwei Zeng, et al. (2023). A shape-attention Pivot-Net for identifying central pivot irrigation systems from satellite images using a cloud computing platform: an application in the contiguous US. GIScience & Remote Sensing, 60(1).

• Fuyou Tian, Bingfang Wu, Hongwei Zeng, et al. (2025). GMIE: a global maximum irrigation extent and central pivot irrigation system dataset derived via irrigation performance during drought stress and deep learning methods. Earth System Scientific Data, 17(3): 855-880.

• Hang Zhao, Bingfang Wu, Miao Zhang, et al. (2025). A large-scale VHR parcel dataset and a novel hierarchical semantic boundary-guided network for agricultural parcel delineation. ISPRS Journal of Photogrammetry and Remote Sensing, 221: 1-19.

• Yifan Li, Fuyou Tian, Miao Zhang, et al. (2025). A 10-meter global terrace mapping using sentinel-2 imagery and topographic features with deep learning methods and cloud computing platform support. International Journal of Applied Earth Observation and Geoinformation, 139: 104528.

• Fuyou Tian, Bingfang Wu, Hongwei Zeng, et al. (2019). Efficient Identification of Corn Cultivation Area with Multitemporal Synthetic Aperture Radar and Optical Images in the Google Earth Engine Cloud Platform. Remote Sensing. 2019, 11, 629.

• Hui Chen, Huapeng Li, Zhao Liu, et al. (2023). A novel Greenness and Water Content Composite Index (GWCCI) for soybean mapping from single remotely sensed multispectral images. Remote Sensing of Environment, 295, 113679.

• Xin Zhang, Wu Bingfang, Ponce-Campos, G.E., et al. (2018) Mapping up-to-Date Paddy Rice Extent at 10 M Resolution in China through the Integration of Optical and Synthetic Aperture Radar Images. Remote Sensing, 10(8), 1200

• Junbin Li, Hongwei Zeng*, Miao Zhang, et al. (2025). A Two-Step Method for Monitoring Annual Paddy Rice Planted Area in Tropical Region by Integrating Rice Identification and Cropping Intensity Estimation. 2025, IEEE Transactions on Geoscience and Remote Sensing. 63, 1-15.

• Yan Xie, Hongwei Zeng, Junbin Li, et al.(2025). Improving parcel level crop classification by integrating a novel red edge maize-cotton mapping index and machine learning: A case study in the Ebinur Lake Basin. International Journal of Applied Earth Observation and Geoinformation. 143:104765.

• Xinli Qin, Bingfang Wu, Hongwei Zeng, et al. (2024). Global Gridded Crop Production Dataset at 10 km Resolution from 2010 to 2020. Scientific Data, 11, 1377

• Bingfang Wu, Zonghan Ma, Nana Yan, et al. (2020). Agricultural drought mitigating indices derived from the changes in drought characteristics. Remote Sensing of Environment, 244, 111813.

• Bingfang Wu, Zonghan Ma, Boken, V. K., et al. (2022). Regional differences in the performance of drought mitigation measures in 12 major wheat-growing regions of the world. Agricultural Water Management, 273, 107888.

• Yuanchao Li, Hongwei Zeng, Miao Zhang, et al. (2023). A county-level soybean yield prediction framework coupled with XGBoost and multidimensional feature engineering. International Journal of Applied Earth Observation and Geoinformation, 118, 103269.

• Yuanchao Li, Hongwei Zeng, Miao Zhang, et al. (2024). Global de-trending significantly improves the accuracy of XGBoost-based county-level maize and soybean yield prediction in the Midwestern United States. GIScience & Remote Sensing, 2024, 61(1).

• Miao Zhang, Bingfang Wu, Hongwei Zeng,et al. (2021). GCI30: A global dataset of 30 m cropping intensity using multisource remote sensing imagery. Earth System Science Data, 13(10), 4799-4817