Weeds are the major biological barriers to achieving higher yields in agro‐ecosystem. We aimed to determine weed community (seedbank and aboveground) and crop yield responses to conventional tillage (CT) and different types of conservation agriculture (CA) practices with variable nitrogen (N) doses in a maize (Zea mays L.)–wheat (Triticum aestivum L.)–mungbean (Vigna radiata L.) rotation. After 8 years of implementation, CA practices including zero‐tilled (ZT) permanent narrow‐bed with crop residues and 100% required N (PNB + R + 100 N), and ZT permanent broad‐bed with residues and 100% required N (PBB + R + 100 N) had a lower weed seed density by 45% at 0–7.5 cm and 53% at 7.5–15 cm soil layers than CT. CT promoted dominance of Cyperus rotundus L., Cyperus esculentus L. and Dinebra retroflexa (Vahl) Panz. while, specific CA practices (PNB + R + 100 N and PBB + R + 100 N) promoted dominance of Digera arvensis Forsk. and Melilotus indicus (L.). Compared to PNB + R + 100 N and PBB + R + 100 N, CT seedbanks had 41–46% higher ecological dominance, which is an indicator that delineates dominance of few specific weed species. The PBB + R + 100 N also had a lower total above‐ground weed density in maize–wheat–mungbean rotation by 34% (mean of years) than CT. The PBB + R + 100 N had 31.1% higher system productivity over CT. Thus, PBB + R + 100 N could reduce the weed seed density in the soil and above‐ground weeds and increase crop yields for sustainable crop production in maize–wheat–mungbean rotations.

Crop phenology monitoring is a necessary action for precision agriculture. Sentinel-1 and Sentinel-2 satellites provide us with the opportunity to monitor crop phenology at a high spatial resolution with high accuracy. The main objective of this study was to examine the potential of the Sentinel-1 and Sentinel-2 data and their combination for monitoring sugarcane phenological stages and evaluate the temporal behaviour of Sentinel-1 parameters and Sentinel-2 indices. Seven machine learning models, namely logistic regression, decision tree, random forest, artificial neural network, support vector machine, naïve Bayes, and fuzzy rule based systems, were implemented, and their predictive performance was compared. Accuracy, precision, specificity, sensitivity or recall, F score, area under curve of receiver operating characteristic and kappa value were used as performance metrics. The research was carried out in the Indo-Gangetic alluvial plains in the districts of Hisar and Jind, Haryana, India. The Sentinel-1 backscatters and parameters VV, alpha and anisotropy and, among Sentinel-2 indices, normalized difference vegetation index and weighted difference vegetation index were found to be the most important features for predicting sugarcane phenology. The accuracy of models ranged from 40 to 60%, 56 to 84% and 76 to 88% for Sentinel-1 data, Sentinel-2 data and combined data, respectively. Area under the ROC curve and kappa values also supported the supremacy of the combined use of Sentinel-1 and Sentinel-2 data. This study infers that combined Sentinel-1 and Sentinel-2 data are more efficient in predicting sugarcane phenology than Sentinel-1 and Sentinel-2 alone.