Varlen Corporation owned and operated two industrial sites that were found to have significant amounts of groundwater contamination related to the sites' operations. When its insurer, Liberty Mutual Insurance Company, refused to indemnify it, Varlen sued. Varlen's case turned on testimony from an expert witness, who was excluded by the district court because he didn't use reliable methods. We agree with the district court's exclusion and affirm its grant of summary judgment to Liberty Mutual.
I.
Varlen, an Illinois corporation, owned and operated two industrial facilities related to railroad operations during the time period relevant to this appeal. At the first, which the parties call the LASI site, Varlen performed operations such as plating parts for locomotive engines in chrome. At the second, the Silvis site, Varlen's operations included refueling diesel engines. Varlen discovered contamination at both sites.
The LASI site was equipped with a sump that held wastewater from the chrome plater. When the water in the sump reached a certain level, a pump would engage, pumping the water to a holding tank. Varlen found a chemical called hexavalent chromium contaminating the area around the sump.
*458At the Silvis site, Varlen discovered two types of groundwater contamination. It found a chlorinated solvent by a tank into which metal parts were dipped to degrease them. It also found diesel fuel near a large tank where locomotives would refuel.
The contamination at these two sites cost Varlen millions of dollars in damages and remediation expenses. Varlen sought indemnification from its insurer, Liberty Mutual. But Varlen's policy with Liberty Mutual had an exclusion for any property damage arising out of chemical leaks or discharges, and Liberty Mutual denied coverage on this ground.
Varlen sued Liberty Mutual. To overcome the pollution exclusion, it pointed to a policy provision stating that, despite the exclusion, Liberty Mutual would cover chemical leaks or discharges that were "sudden and accidental." Lacking direct evidence of how the damage occurred, it proffered the expert testimony of geologist Daniel Rogers to prove that the contamination of the LASI and Silvis sites occurred suddenly and accidentally.
Rogers testified that the contaminants at the LASI site were released because the concrete sump leaked. He opined that the releases were "sudden and accidental" because they were not intended and occurred in sudden spurts each time that the sump failed. When asked about his basis for these opinions, he explained that he had experience working with sumps and had personal knowledge of these sumps in particular.
Rogers also testified that the releases at the Silvis site were likely "sudden and accidental." There are two relevant zones at the Silvis site: the area around the diesel refueling station and the area where the chlorinated solvents were stored. Rogers asserted that the contamination around the diesel refueling area was too large to have occurred by minor leakage. Instead, he testified that the contamination was "consistent with overfills of diesel locomotives" and suggested that "tens of gallons to hundreds of gallons [ ] would have been released before it was noticed." He also said that the value of the fuel made it unlikely that such a fuel spill would have occurred intentionally. Turning to the contamination at the chlorinated solvent storing area, Rogers surmised that it was "indicative of a drum overturning and suddenly leaking out rather than from operations." He based this opinion in part on the fact that the contamination was found around where the solvent was stored, not where it was used.
Both parties moved for summary judgment. Liberty Mutual also moved to strike Rogers's testimony. The district court granted the motion to strike, holding that Rogers's opinions were unreliable and speculative under Federal Rule of Evidence 702. It then granted Liberty Mutual's motion for summary judgment. Varlen appealed.
II.
Liberty Mutual is entitled to summary judgment against Varlen if no reasonable jury could find that the releases were "sudden and accidental" at either the LASI or Silvis sites. See FED. R. CIV. P. 56(a) ; Anderson v. Liberty Lobby, Inc. , 477 U.S. 242, 255-56, 106 S.Ct. 2505, 91 L.Ed.2d 202 (1986). And Liberty Mutual correctly asserts that Varlen has pointed to no admissible evidence that would permit a reasonable jury to make that finding.
Rogers's expert testimony is the only evidence that Varlen offered as to whether the contamination occurred in a *459sudden and accidental fashion.1 But before Rogers's expert testimony can be admitted, it must be deemed reliable under Rule 702 of the Federal Rules of Evidence, which tracks the Supreme Court's opinion in Daubert v. Merrell Dow Pharmaceuticals, Inc. , 509 U.S. 579, 113 S.Ct. 2786, 125 L.Ed.2d 469 (1993). The court must decide that the witness is "qualified as an expert by knowledge, skill, experience, training, or education"; the testimony will "help the trier of fact to understand the evidence or to determine a fact in issue"; "the testimony is based on sufficient facts or data" and "reliable principles and methods"; and the expert has "reliably applied the principles and methods to the facts of the case." FED. R. EVID. 702. An expert's proponent has the burden of establishing the admissibility of the opinions by a preponderance of the evidence. See Lewis v. CITGO Petroleum Corp. , 561 F.3d 698, 705 (7th Cir. 2009).
The district court determined that Rogers's testimony did not meet these requirements because it was not based on reliable methods or principles. It did not abuse its discretion in reaching that conclusion. See Brown v. Burlington N. Santa Fe Ry. Co. , 765 F.3d 765, 772 (7th Cir. 2014) ("If the court properly [followed the Daubert framework], we then review its ultimate decision to exclude expert testimony for an abuse of discretion.").
In Rogers's report and testimony, he asserted that the discharges at the LASI site must have been "sudden and accidental." He suspected that the contamination occurred in connection with a failure in the sump pump in the 1970s. He claimed to base this on his experience with sumps, his site visits, and his knowledge of the sites' operations. This type of evidence is not necessarily unreliable. See Metavante Corp. v. Emigrant Sav. Bank , 619 F.3d 748, 761 (7th Cir. 2010) ("An expert's testimony is not unreliable simply because it is founded on his experience rather than on data."). But Rogers still needed to show how his experience or expertise led to his conclusions.
Rogers attempted to base his conclusions on inferences from qualities of the "plume" of contamination. That is, he looked at the size and scope of the contamination and worked backward to surmise how it must have occurred. For instance, Rogers testified that at the LASI site, the contaminant mass must have been very large to create a plume with the size and concentration of the one at that site. He concluded that the contamination must have therefore been sudden and accidental.
But Rogers failed to explain why this data mattered or why his inferences were justified. When pressed specifically on the connection between the contaminant mass and the circumstances of the release, he simply stated that the data was "an indication" but acknowledged that it was "not conclusive." He opined that the sump itself had a "sudden and accidental nature." But it's not clear what he meant, considering that the sump is just a basin in the ground. Rogers did say in passing that the contamination concentrations were "not uniform," but he didn't explain why that was significant.
Rogers's testimony about the Silvis site was equally lacking. He said that the volume of the contamination at the fueling *460location was inconsistent with "minor leakage" and opined instead that it may have resulted from overfills of diesel locomotives. As to the chlorinated solvent storing area, Rogers suggested that perhaps a drum got punctured and caused the contamination. But Rogers offered no methodology to explain how he drew those conclusions.
In short, Rogers failed to demonstrate that his conclusions were anything more than guesses. To satisfy Daubert , Rogers needed to provide an explanation of how the evidence led to his conclusions. He had to articulate a justification for his inference that the chemical spills were sudden and accidental beyond a simple say-so. If Rogers made an argument based on a reliable methodology, then Varlen has not pointed it out, either to us or to the district court. And courts do not have to scour the record or make a party's argument for it. See D.Z. v. Buell , 796 F.3d 749, 756 (7th Cir. 2015). The district court did not abuse its discretion in excluding Rogers's testimony. And without Rogers's testimony and report, there is no issue of material fact as to whether the contamination occurred suddenly and accidentally.2 See Celotex Corp. v. Catrett , 477 U.S. 317, 322, 106 S.Ct. 2548, 91 L.Ed.2d 265 (1986) (" Rule 56(c) mandates the entry of summary judgment ... against a party who fails to make a showing sufficient to establish the existence of an element essential to that party's case, and on which that party will bear the burden of proof at trial."). We thus AFFIRM the district court's grant of summary judgment to Liberty Mutual.3