Crop residue plays a crucial role in diverse areas of soil, biomass, crop yield, and the environment by impacting aspects such as soil organic matter, erosion, nutrient leaching, soil moisture and temperature, plant emergence, in turn influencing plant biomass and crop yields. Measuring crop residue coverage has been a long-term practice, primarily for monitoring purposes by agencies for various programs. More recently, increased research effort has been focused on improving the means and mechanisms of measuring and sensing crop residue efficiently and on large scales for both monitoring and improved agricultural decision-making insights. This review attempts to provide an overview of crop residue measurement and sensing, presenting a holistic review of the different measurement techniques available. It also highlights how research has shifted from field-based measurement to the use of diverse sensing approaches and future directions. Traditional methods of crop residue measurement are reviewed and the literature on more modern sensing approaches is summarized through categorization of the approaches based on sensing scale of satellite-, UAV-, and ground-based systems. Key findings highlight the growing shift toward high-resolution UAV sensing and the increasing use of machine learning models for improved classification. Identified critical challenges, particularly in satellite sensing, include spectral similarity between residue and soil, influence of moisture, and limited real-time application. The review aims to provide a summary of the current state of crop residue sensing with insights into potential areas for opportunities, especially through on-machine sensing systems, emphasizing the need for real-time, integrated, and adaptive residue coverage sensing solutions.

Crop residue plays a significant role on soil health, nutrient cycling, and crop yield, making residue management a key consideration in agricultural production. This review aims to synthesize current knowledge on two different aspects of crop residue in grain production systems: common management practices and their effects. A comprehensive literature survey was conducted using the Scopus database, covering worldwide publications from 1990 to 2025. First, this review explores various crop residue management practices, including burning, stubble retention, and different tillage methods (conservation tillage vs. conventional tillage). This section mainly focuses on tillage practices with an emphasis on the environmental, economic, and agronomic consequences of each approach. Then this review paper explores the effects of crop residue on soils and ecosystems, including the role of crop residues in improving soil quality and enhancing soil organic carbon sequestration. The interaction between crop residues and hydrological processes such as water infiltration and runoff is also examined in this section. The relationships between residue management practices and crop growth and yield responses are also critically assessed. This review highlights the shift from conventional, environmentally detrimental practices toward conservation-oriented approaches, especially reduced tillage, no tillage, and residue retention. Key knowledge gaps and research priorities are identified, particularly regarding crop residue effects on deep soil carbon sequestration, hydrology, crop growth and yields, and the lack of practical management guidelines across agroecosystems. This review provides an integrated framework to support crop residue management and guide future research in conservation agriculture.

Crop residue management is critical for soil conservation and agricultural productivity. Growers actively manage the crop residue in their fields based on experiential observation; however, residue management has thus far been largely omitted from typical modern precision agriculture workflows due to the lack of reliable sensing. The widely used baseline method for measuring crop residue coverage (CRC), the manual line-transect method, requires manual fieldwork that limits its utility. Other methods for CRC measurement and estimation rely on orthoimagery, which neglects the potential use of on-machine imagery collected during agricultural operations. This study first analyzes the accuracy of the manual line-transect method and develops alternatives for measuring CRC using images captured by onboard cameras during tillage operations. The proposed virtual scatter method is shown to achieve a standard deviation of 3.7% compared to the manual line-transect method. Then, the virtual scatter method is subsequently employed to generate CRC labels for an image dataset, in which residue pixels were annotated. Residue masks are then generated at two resolutions (pixel-level and superpixel-level) and used as inputs to segmentation models. A comparison of various machine learning techniques to estimate CRC using on-machine imagery, including Support Vector Machine (SVM), Random Forest (RF), and Entangled Random Forest (ERF) at two different resolutions, is presented. The results demonstrate the superior performance of the ERF model at the superpixel level compared to traditional SVM and RF models, in addition to reduced compute times.

Crop residue management is a critical aspect of sustainable agriculture, affecting soil health, nutrient cycling, and environmental quality. Accurately measuring the crop residue present in the fields before and after tillage operation will help farmers plan their activity accordingly. Various methods for measuring and sensing crop residue, including traditional techniques like the line-transect method, photographic approaches, thresholding-based machine learning models, and more advanced deep learning methods, are available. However, each of these approaches has limitations in terms of accuracy, efficiency, and resource requirements. In this study, we present a unique approach of residue image data collection with a range of crop residue levels using on-machine sensors to capture RGB images from mono cameras. The multi-season and multi-year dataset of more than 25,000 images thus collected is then utilized for supervised machine learning using pretrained ResNet18 model. Using both in-field line transect method and photographic method as ground truth, model accuracy was tested in different scenarios for predicting the crop residue cover. The model predicted CRC into 5 broader classes of 0-20%, 21-35%, 36-55%, 56-75%, and 76-100% CRC. A test accuracy of 85.8% and 61.8% was achieved for same field images and new field images, respectively. A broader evaluation metric, the ’Delta±1 accuracy’ criteria is introduced to describe model performance with wider class tolerances to account for cases where the model’s prediction is close to the ground truth. An accuracy of 99.1% and 93.5% was achieved for same field images, and new field images respectively using the Delta±1 criteria. This study presents a novel approach to crop residue estimation using the crop residue imagery dataset, which could enable real-time sensing of crop residue via on-machine sensors.